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

    Neuronpedia

    INDEX
    Explanations

    numbers around one

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.80
    ,
    0.79
    M
    0.76
    在
    0.71
    ING
    0.71
    Q
    0.65
    s
    0.65
    ii
    0.64
    Z
    0.63
    も
    0.63
    POSITIVE LOGITS
    ного
    0.73
    1
    0.71
    cido
    0.69
    ır
    0.65
    า
    0.64
    к
    0.64
     decoración
    0.62
    েন
    0.62
    োডে
    0.62
     récupération
    0.62
    Act Density 0.484%

    No Known Activations