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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wide
    -0.08
     race
    -0.07
     physicians
    -0.07
     East
    -0.07
    (fileName
    -0.07
    Statistics
    -0.07
    Ids
    -0.07
    干
    -0.07
    akeFromNib
    -0.07
    abytes
    -0.07
    POSITIVE LOGITS
     Abbott
    0.07
     seb
    0.06
     توم
    0.06
    .enum
    0.06
     Велик
    0.06
     olacağ
    0.06
    _grupo
    0.06
     σει
    0.06
     thay
    0.06
     VL
    0.05
    Act Density 0.022%

    No Known Activations