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

    Neuronpedia

    INDEX
    Explanations

    programming language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.61
    faulse
    0.59
     watersheds
    0.59
    נ
    0.58
    могою
    0.57
     مع
    0.57
    casualties
    0.56
     unsettled
    0.56
     درواز
    0.56
    愘
    0.56
    POSITIVE LOGITS
    ?
    0.55
    地方
    0.53
    。
    0.51
    Revelation
    0.50
    bb
    0.50
    cc
    0.49
    资料
    0.49
    Vitamin
    0.49
    I
    0.49
    ée
    0.48
    Act Density 0.000%

    No Known Activations