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

    Neuronpedia

    INDEX
    Explanations

    display/check computer settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avez
    -0.09
     embody
    -0.08
    打造
    -0.08
    بت
    -0.08
     gồm
    -0.08
     pillars
    -0.08
     namely
    -0.08
     Introdu
    -0.07
     demokrat
    -0.07
    skraft
    -0.07
    POSITIVE LOGITS
    を見る
    0.15
    查看
    0.14
     查看
    0.14
     reveals
    0.13
     revealing
    0.13
     reveal
    0.13
     dettagli
    0.11
     anzeigen
    0.11
     Reve
    0.11
    看看
    0.10
    Act Density 0.025%

    No Known Activations