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

    Neuronpedia

    INDEX
    Explanations

    celebrity names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒀝
    0.39
     సామ
    0.38
     聞い
    0.37
     來
    0.37
     和
    0.36
    BackgroundHelper
    0.36
    uetooth
    0.34
    arrison
    0.34
    ブラウン
    0.33
    BleStatus
    0.33
    POSITIVE LOGITS
    x
    0.59
    n
    0.57
    m
    0.54
    and
    0.52
    j
    0.50
    o
    0.45
    z
    0.45
    in
    0.45
    et
    0.44
    it
    0.44
    Act Density 0.005%

    No Known Activations