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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash

    This neuron detects academic reference/citation markers (e.g., bracketed author–year or numbered citations) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    鲁
    -0.06
    ニニ
    -0.06
    Squared
    -0.06
     vivo
    -0.06
     Fowler
    -0.06
    .increment
    -0.06
     dropping
    -0.06
     Axe
    -0.06
    Psi
    -0.06
    anticipated
    -0.06
    POSITIVE LOGITS
     cocks
    0.07
    adal
    0.06
    InstanceState
    0.06
     เจ
    0.06
    PullParser
    0.06
    .password
    0.06
     balk
    0.06
     inputStream
    0.06
    .ship
    0.06
     кого
    0.06
    Act Density 0.019%

    No Known Activations