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

    Neuronpedia

    INDEX
    Explanations

    device count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ில்
    0.52
    icheskoj
    0.49
    JlcG
    0.47
     கடுமையான
    0.46
    ukkig
    0.46
    નને
    0.46
    apayati
    0.46
     уйнарга
    0.45
     הע
    0.45
    estä
    0.45
    POSITIVE LOGITS
    式
    0.63
    8
    0.60
    ش
    0.60
    2
    0.60
    器
    0.59
    6
    0.58
    sq
    0.57
    数
    0.57
     مين
    0.56
    3
    0.56
    Act Density 0.021%

    No Known Activations