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

    Neuronpedia

    INDEX
    Explanations

    object deleted successfully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     വിശ്വാ
    0.94
    𒊒
    0.91
    𒌨
    0.91
     বজায়
    0.89
    StartPosition
    0.88
     abstinence
    0.87
     possession
    0.86
     vergessen
    0.85
    碛
    0.85
     detection
    0.85
    POSITIVE LOGITS
    การ
    0.69
    M
    0.64
     to
    0.59
     ت
    0.59
     การ
    0.58
    ize
    0.58
     الم
    0.57
     M
    0.57
     ف
    0.57
     successfully
    0.56
    Act Density 1.050%

    No Known Activations