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

    Neuronpedia

    INDEX
    Explanations

    o

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reputation
    -0.07
    _mes
    -0.06
    цей
    -0.06
     způsobem
    -0.06
     Robot
    -0.06
     答
    -0.06
    ią
    -0.06
    xr
    -0.06
     milling
    -0.05
    @↵
    -0.05
    POSITIVE LOGITS
     hen
    0.07
     liner
    0.07
    .lookup
    0.07
     Railroad
    0.07
    zhou
    0.06
     Vaugh
    0.06
     RESOURCE
    0.06
     yards
    0.06
     обработ
    0.06
     Enh
    0.06
    Act Density 0.009%

    No Known Activations