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

    Neuronpedia

    INDEX
    Explanations

    том

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .card
    -0.07
    ег
    -0.06
    (levels
    -0.06
    Pay
    -0.06
     Bring
    -0.06
    connect
    -0.06
    ,{
    -0.06
    asket
    -0.06
     شهرستان
    -0.06
     Arg
    -0.06
    POSITIVE LOGITS
    ."},↵
    0.08
    ‌دهد
    0.08
     работает
    0.08
     donn
    0.07
     того
    0.07
    ITLE
    0.07
    曰
    0.07
     WELL
    0.07
     이루
    0.07
     том
    0.07
    Act Density 0.027%

    No Known Activations