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

    Neuronpedia

    INDEX
    Explanations

    cancellation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     joys
    -0.08
     любов
    -0.06
     йому
    -0.06
    /image
    -0.06
    ickers
    -0.06
    styl
    -0.06
    ичної
    -0.06
    combat
    -0.06
    ehicle
    -0.06
    :on
    -0.06
    POSITIVE LOGITS
     groundwork
    0.07
    (uint
    0.07
    _logits
    0.07
     anticipated
    0.07
     StatusCode
    0.06
     контролю
    0.06
     offseason
    0.06
    =True
    0.06
    hammer
    0.06
     Tulsa
    0.06
    Act Density 0.000%

    No Known Activations