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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    钓
    -0.07
    cov
    -0.07
    扣
    -0.07
    遵义
    -0.07
    nge
    -0.07
    _REV
    -0.07
    .atan
    -0.07
     applying
    -0.06
    .assign
    -0.06
    奭
    -0.06
    POSITIVE LOGITS
     oud
    0.07
    .getColumnModel
    0.07
     Klan
    0.07
    �
    0.07
    岍
    0.06
     piano
    0.06
    _GRAY
    0.06
    より
    0.06
    稀缺
    0.06
     doubly
    0.06
    Act Density 0.064%

    No Known Activations