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

    Neuronpedia

    INDEX
    Explanations

    simple

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fill
    -0.07
    .checkbox
    -0.07
    GetPosition
    -0.07
    .Begin
    -0.07
     Param
    -0.06
     Cov
    -0.06
     vigilant
    -0.06
     송
    -0.06
    _corners
    -0.06
     Δι
    -0.06
    POSITIVE LOGITS
     erased
    0.07
     imageName
    0.07
     naj
    0.07
    เก
    0.07
     رسمی
    0.06
    뮤
    0.06
    aben
    0.06
     výro
    0.06
     eiusmod
    0.06
     +**************
    0.06
    Act Density 0.052%

    No Known Activations