Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t detect or respond to any token patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    the neuron detects interrogative/question cues — tokens that start or appear in questions (question words and auxiliaries used to form questions).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     overtime
    -0.07
    .setPassword
    -0.07
    Var
    -0.07
    Tel
    -0.06
    ilities
    -0.06
    _RED
    -0.06
     bán
    -0.06
     waktu
    -0.06
    еч
    -0.06
    alara
    -0.06
    POSITIVE LOGITS
     Shall
    0.07
     theorem
    0.07
     Mourinho
    0.06
    agog
    0.06
    andscape
    0.06
     GOOD
    0.06
     Mechan
    0.06
    erdem
    0.06
     olumsuz
    0.06
    Sexy
    0.06
    Act Density 0.118%

    No Known Activations