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

    Neuronpedia

    INDEX
    Explanations

    markup id attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >
    -1.72
    C
    -1.63
    してます
    -1.63
    In
    -1.60
    x
    -1.56
    líben
    -1.46
    2
    -1.46
     Makes
    -1.44
    As
    -1.44
     to
    -1.42
    POSITIVE LOGITS
    嗵
    2.05
    䛗
    1.92
    嘡
    1.91
    馓
    1.88
     adem
    1.82
     heren
    1.77
     kado
    1.75
     simpel
    1.73
     aussit
    1.72
     artikel
    1.71
    Act Density 0.006%

    No Known Activations