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

    Neuronpedia

    INDEX
    Explanations

    learning English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tutto
    -0.06
    .request
    -0.06
     Scots
    -0.06
    Slider
    -0.06
    меть
    -0.06
     필요한
    -0.06
     дії
    -0.06
     Identity
    -0.06
     цей
    -0.06
    .Filter
    -0.06
    POSITIVE LOGITS
    ='".
    0.07
     kappa
    0.07
     maj
    0.06
     KV
    0.06
    SEM
    0.06
     divis
    0.06
     gradient
    0.06
    popover
    0.06
    `='$
    0.06
    おり
    0.06
    Act Density 0.047%

    No Known Activations