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

    Neuronpedia

    INDEX
    Explanations

    estimated time of arrival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    only
    0.61
    بل
    0.57
    संख्या
    0.57
    clickView
    0.57
    number
    0.57
    城市
    0.56
    fb
    0.55
    σουν
    0.54
    ند
    0.54
    اج
    0.53
    POSITIVE LOGITS
     on
    0.73
     אי
    0.59
     לת
    0.58
     modules
    0.57
     estimation
    0.53
     degraded
    0.53
     degener
    0.53
     high
    0.52
     ת
    0.52
     factor
    0.52
    Act Density 0.000%

    No Known Activations