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

    Neuronpedia

    INDEX
    Explanations

    disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لیکن
    0.90
    لمانية
    0.78
    తాయి
    0.77
    uous
    0.76
    Suc
    0.76
     inmediatamente
    0.74
    ați
    0.74
    limegreen
    0.74
    しかし
    0.72
    このように
    0.71
    POSITIVE LOGITS
     for
    0.88
    리
    0.88
     CAF
    0.86
     PayPal
    0.85
     Ether
    0.83
     Skype
    0.82
     FOR
    0.81
    ור
    0.81
     রি
    0.81
     заинтере
    0.79
    Act Density 0.218%

    No Known Activations