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

    Neuronpedia

    INDEX
    Explanations

    you will act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erview
    0.46
     Buk
    0.40
    杷
    0.40
    Transfer
    0.39
    ارهای
    0.39
     Differentiation
    0.38
    的行为
    0.37
    BeforeCall
    0.37
    行為
    0.36
     conférence
    0.36
    POSITIVE LOGITS
     por
    0.44
     poz
    0.42
     devils
    0.40
     Y
    0.39
     поз
    0.38
     подпис
    0.38
    美女
    0.37
     satt
    0.37
     Yen
    0.37
    devil
    0.37
    Act Density 0.003%

    No Known Activations