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

    Neuronpedia

    INDEX
    Explanations

    Tele

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Investments
    -0.07
    ющим
    -0.07
     jeep
    -0.06
     Airbnb
    -0.06
     Washington
    -0.06
    elter
    -0.06
    тур
    -0.06
    ैप
    -0.06
     Cum
    -0.06
    psz
    -0.06
    POSITIVE LOGITS
     scoff
    0.07
     inicio
    0.07
    pering
    0.07
    InRange
    0.06
    illage
    0.06
     annotated
    0.06
     exited
    0.06
    RIX
    0.06
    .getenv
    0.06
     ninety
    0.06
    Act Density 0.225%

    No Known Activations