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

    Neuronpedia

    INDEX
    Explanations

    .plugins

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    浴室
    -0.07
    qb
    -0.07
     côté
    -0.07
    廖
    -0.07
    转身
    -0.06
    몴
    -0.06
    facet
    -0.06
    inez
    -0.06
    忘了
    -0.06
    .getMonth
    -0.06
    POSITIVE LOGITS
     Declaration
    0.08
    严谨
    0.07
    队伍
    0.07
    存货
    0.07
    .ResponseBody
    0.07
    Encoder
    0.07
    leness
    0.06
    ⋋
    0.06
    _ident
    0.06
    _nums
    0.06
    Act Density 0.000%

    No Known Activations