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

    Neuronpedia

    INDEX
    Explanations

    fixed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ય
    1.92
    ce
    1.71
    ल
    1.70
    为止
    1.64
     objections
    1.63
     arcs
    1.63
    जन्य
    1.61
    1.60
     estuaries
    1.59
    дин
    1.57
    POSITIVE LOGITS
    s
    1.88
    ても
    1.84
    idious
    1.70
    ol
    1.66
    ात
    1.64
    ees
    1.63
    ك
    1.62
    ीय
    1.60
     जानिए
    1.56
    eda
    1.55
    Act Density 0.005%

    No Known Activations