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

    Neuronpedia

    INDEX
    Explanations

    code and technical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whisper
    -0.06
    ères
    -0.06
     misunderstand
    -0.06
    하고
    -0.06
    .req
    -0.06
    (Constant
    -0.06
     Degree
    -0.06
    Extern
    -0.06
    -même
    -0.06
     fase
    -0.06
    POSITIVE LOGITS
    VEL
    0.08
     Mortgage
    0.06
    》↵
    0.06
     leverage
    0.06
    �
    0.06
     repayment
    0.06
    альную
    0.06
     stalk
    0.06
    计算
    0.06
    nite
    0.06
    Act Density 0.007%

    No Known Activations