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

    Neuronpedia

    INDEX
    Explanations

    say "al word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ailability
    -0.07
    uncture
    -0.07
     sonrasında
    -0.06
    lda
    -0.06
     ldc
    -0.06
    partials
    -0.06
     Congressman
    -0.06
    CanBe
    -0.06
    最近
    -0.06
    fuck
    -0.06
    POSITIVE LOGITS
    (rad
    0.07
     ration
    0.07
    kategori
    0.07
     участ
    0.07
     Guitar
    0.06
    ensual
    0.06
    齐
    0.06
     skirt
    0.06
     MatDialog
    0.06
    增
    0.06
    Act Density 0.001%

    No Known Activations