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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Highlight
    -0.07
    (A
    -0.06
     negligible
    -0.06
    fecha
    -0.06
    .dependencies
    -0.06
    [last
    -0.06
     Diese
    -0.06
     neboť
    -0.06
     Gravity
    -0.06
     DISABLE
    -0.06
    POSITIVE LOGITS
     prayers
    0.07
    .zh
    0.07
     propio
    0.06
    ')):↵
    0.06
    όγ
    0.06
     전쟁
    0.06
    わ
    0.06
     DIS
    0.06
     intoler
    0.06
    .xx
    0.06
    Act Density 0.033%

    No Known Activations