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

    Neuronpedia

    INDEX
    Explanations

    named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horizons
    -0.08
     HIM
    -0.07
    LAM
    -0.07
     China's
    -0.07
     Environmental
    -0.07
    WER
    -0.07
     Parque
    -0.07
    مي
    -0.07
    Environmental
    -0.07
    ुण
    -0.07
    POSITIVE LOGITS
     ושל
    0.08
     ولك
    0.08
     anyway
    0.08
     whatsoever
    0.08
     oda
    0.08
     независимо
    0.08
     eftersom
    0.08
     станов
    0.07
     hare
    0.07
    乃
    0.07
    Act Density 0.303%

    No Known Activations