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

    Neuronpedia

    INDEX
    Explanations

    babysitting or washers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ס
    0.67
    ot
    0.67
    ли
    0.62
    elems
    0.61
    ال
    0.57
    ции
    0.56
    гне
    0.56
     постоян
    0.55
    ר
    0.55
     Monetary
    0.53
    POSITIVE LOGITS
    ्ट
    0.79
    inness
    0.69
    k
    0.69
    ly
    0.67
    ifiably
    0.67
    ння
    0.66
    lerden
    0.66
    lerle
    0.66
     efficacement
    0.65
    クサ
    0.65
    Act Density 0.000%

    No Known Activations