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

    Neuronpedia

    INDEX
    Explanations

    advanced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Quando
    -1.86
     素描
    -1.79
     vijf
    -1.79
    カッコいい
    -1.77
    dessin
    -1.75
    皤
    -1.74
    nouveau
    -1.73
     vivent
    -1.71
     trám
    -1.71
     différents
    -1.70
    POSITIVE LOGITS
    s
    2.47
    _
    2.19
    Even
    2.14
     uses
    2.13
    After
    2.06
     takes
    2.00
    During
    1.95
    With
    1.92
    .
    1.91
    世紀
    1.90
    Act Density 0.020%

    No Known Activations