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

    Neuronpedia

    INDEX
    Explanations

    ense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Debate
    -0.07
     Deployment
    -0.06
    _Man
    -0.06
     transformation
    -0.06
     approx
    -0.06
    466
    -0.06
     Maiden
    -0.06
    mouseover
    -0.06
     soared
    -0.06
    .LogWarning
    -0.06
    POSITIVE LOGITS
     vữ
    0.06
    /bus
    0.06
    >(*
    0.06
     medida
    0.06
     busted
    0.06
    otlin
    0.06
     seria
    0.06
    :NS
    0.06
     okolí
    0.06
    eníze
    0.06
    Act Density 0.002%

    No Known Activations