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

    Neuronpedia

    INDEX
    Explanations

    incrementing counters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ות
    0.75
    grund
    0.69
    ać
    0.64
    NCR
    0.62
    меня
    0.62
    ness
    0.62
    y
    0.61
    ycle
    0.61
     ಏಕೆಂದರೆ
    0.60
    aan
    0.60
    POSITIVE LOGITS
    argc
    0.82
    к
    0.80
     Tempat
    0.74
     угла
    0.72
     fal
    0.67
     riv
    0.67
     dots
    0.66
     ferv
    0.65
     collisional
    0.65
     раст
    0.65
    Act Density 0.273%

    No Known Activations