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

    Neuronpedia

    INDEX
    Explanations

    claims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Inter
    -0.07
    дет
    -0.07
     pep
    -0.06
    Λ
    -0.06
     smith
    -0.06
     dec
    -0.06
    contact
    -0.06
    ERA
    -0.06
     Кон
    -0.06
    <Token
    -0.06
    POSITIVE LOGITS
    ionage
    0.07
     �
    0.06
     dirname
    0.06
     ningún
    0.06
     společ
    0.06
     Sustainability
    0.06
    uity
    0.06
     Sorting
    0.06
    _TMP
    0.06
    ágina
    0.06
    Act Density 0.011%

    No Known Activations