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

    Neuronpedia

    INDEX
    Explanations

    character descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Piano
    -0.07
    (a
    -0.07
     Marian
    -0.07
    Ace
    -0.07
    sg
    -0.06
    Customers
    -0.06
    .x
    -0.06
    _CC
    -0.06
    .Α
    -0.06
    anı
    -0.06
    POSITIVE LOGITS
     внут
    0.07
    gratis
    0.07
     Fonts
    0.06
    加入
    0.06
    (sock
    0.06
    关系
    0.06
     Sponsored
    0.06
    weight
    0.06
     soy
    0.06
     ↵↵
    0.06
    Act Density 0.017%

    No Known Activations