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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yster
    -0.09
     param
    -0.08
    _STAGE
    -0.08
     동
    -0.08
     государственной
    -0.08
     etabl
    -0.08
    லாம்
    -0.07
    ்வே
    -0.07
     PEM
    -0.07
     existir
    -0.07
    POSITIVE LOGITS
     Avery
    0.08
     Jill
    0.08
    ignation
    0.07
     Minnie
    0.07
    Opponent
    0.07
    Ready
    0.07
     pune
    0.07
    Good
    0.07
     turi
    0.07
    ña
    0.07
    Act Density 0.000%

    No Known Activations