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

    Neuronpedia

    INDEX
    Explanations

    route / human / experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [][
    0.45
    ()[
    0.44
    [:]
    0.41
     [-
    0.40
    [][]
    0.39
     كبيرة
    0.39
    deps
    0.39
    怎样
    0.39
     [_
    0.39
    locationX
    0.39
    POSITIVE LOGITS
     umet
    0.45
    მ
    0.41
    МИ
    0.40
     Komitet
    0.39
    來講
    0.38
    ופי
    0.38
    搛
    0.38
    光的
    0.37
     മാ
    0.36
    講
    0.36
    Act Density 0.000%

    No Known Activations