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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iyoruz
    -0.07
    >\↵
    -0.07
    atat
    -0.06
    .Binary
    -0.06
    stead
    -0.06
     tiế
    -0.06
    .seq
    -0.06
     Saul
    -0.06
     dị
    -0.06
    のだろう
    -0.06
    POSITIVE LOGITS
    oid
    0.08
     الموقع
    0.06
     Bell
    0.06
     حجم
    0.06
    resultado
    0.06
     eta
    0.06
    EMPL
    0.06
    .backends
    0.06
    _buttons
    0.06
     costs
    0.06
    Act Density 0.005%

    No Known Activations