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

    Neuronpedia

    INDEX
    Explanations

    Science/Web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.91
     للاسماء
    -0.87
     MeV
    -0.85
    InitVars
    -0.84
     themſelves
    -0.82
    Obrázky
    -0.82
    eseorang
    -0.81
     againſt
    -0.81
    ]='\
    -0.81
    WritableDatabase
    -0.79
    POSITIVE LOGITS
    p
    0.56
    l
    0.53
    y
    0.52
     p
    0.52
    ?
    0.48
    m
    0.48
     '
    0.47
    f
    0.47
     c
    0.47
    let
    0.46
    Act Density 1.820%

    No Known Activations