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

    Neuronpedia

    INDEX
    Explanations

    generalized technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    佮
    -2.69
    蕷
    -2.39
    ☆☆☆☆
    -2.38
     ruban
    -2.36
    GEBUR
    -2.34
     прошел
    -2.33
    🅣
    -2.28
    鹛
    -2.25
    🫢
    -2.25
    いない
    -2.25
    POSITIVE LOGITS
    1
    3.89
    //
    3.41
    d
    3.36
     =
    3.25
    3
    3.23
    2
    3.16
    7
    3.03
    6
    3.02
    4
    2.95
    In
    2.84
    Act Density 0.004%

    No Known Activations