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

    Neuronpedia

    INDEX
    Explanations

    blaming, chasing losses, or language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Betting
    0.89
     betting
    0.84
     यूजर्स
    0.81
     אשר
    0.78
     fintech
    0.77
     bet
    0.77
    Bet
    0.75
     aktuell
    0.75
     كافة
    0.74
     noteworthy
    0.74
    POSITIVE LOGITS
    .").
    1.08
    '".
    0.97
    }^{*}$.
    0.95
    ائیں۔
    0.93
    ³.
    0.93
    }$.
    0.91
    ''.
    0.91
    .".
    0.91
    ’.”
    0.90
    '."
    0.88
    Act Density 0.005%

    No Known Activations