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

    Neuronpedia

    INDEX
    Explanations

    Abbreviation

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the substring “PT” (as in “GPT”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ilerine
    -0.07
     Olson
    -0.07
     Han
    -0.07
     mer
    -0.07
    _AUTH
    -0.06
    าห
    -0.06
    766
    -0.06
     Adoles
    -0.06
    .INVISIBLE
    -0.06
     bara
    -0.06
    POSITIVE LOGITS
     upt
    0.07
    �
    0.07
    mektedir
    0.07
    judul
    0.07
     Canterbury
    0.06
     ".");↵
    0.06
    mpz
    0.06
     patrol
    0.06
     ATP
    0.06
    <p
    0.06
    Act Density 0.009%

    No Known Activations