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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    The neuron is effectively inactive—it does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     开
    -0.07
    .signIn
    -0.07
     iler
    -0.06
     Sext
    -0.06
     Samuel
    -0.06
    akov
    -0.06
     Commons
    -0.06
     Ezek
    -0.06
     Αρχ
    -0.06
     Simpsons
    -0.06
    POSITIVE LOGITS
     validations
    0.08
    Bool
    0.07
     clearer
    0.06
     оч
    0.06
    .ReadString
    0.06
    けた
    0.06
    _TR
    0.06
    TIMER
    0.06
     �
    0.06
     chunk
    0.06
    Act Density 0.015%

    No Known Activations