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

    Neuronpedia

    INDEX
    Explanations

    REST

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .good
    -0.08
    .and
    -0.08
    _correction
    -0.07
    .vs
    -0.07
    _drive
    -0.07
    .department
    -0.07
    营造良好
    -0.07
    _given
    -0.06
    isodes
    -0.06
     Av
    -0.06
    POSITIVE LOGITS
    管理办法
    0.07
     saliva
    0.07
    FileInfo
    0.07
    有权
    0.07
     Arte
    0.06
    Lite
    0.06
    봊
    0.06
    CN
    0.06
    שילוב
    0.06
    pth
    0.06
    Act Density 0.003%

    No Known Activations