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

    Neuronpedia

    INDEX
    Explanations

    еще

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     free
    -0.08
     freely
    -0.07
     shirt
    -0.07
    _linear
    -0.07
     Shapiro
    -0.07
    _layers
    -0.06
     playground
    -0.06
     Giấy
    -0.06
    owski
    -0.06
     Newman
    -0.06
    POSITIVE LOGITS
    ér
    0.07
    ети
    0.07
     posledních
    0.07
     hiç
    0.06
    _sess
    0.06
     EK
    0.06
    nám
    0.06
    /tasks
    0.06
    addAll
    0.06
     Encore
    0.06
    Act Density 0.013%

    No Known Activations