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

    Neuronpedia

    INDEX
    Explanations

    que se

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأمر
    1.10
    ו
    1.04
    ર
    1.01
    कर्ता
    0.97
    rição
    0.92
    ு
    0.88
    levance
    0.88
    }$
    0.86
    ப
    0.85
    sighted
    0.85
    POSITIVE LOGITS
    나
    1.11
     sapply
    1.06
    iskt
    1.05
     hasten
    0.99
     Carmen
    0.94
    TA
    0.94
    lana
    0.94
    ressions
    0.93
    ik
    0.93
     bicovariant
    0.92
    Act Density 0.001%

    No Known Activations