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

    Neuronpedia

    INDEX
    Explanations

    list introductions and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ก็
    -2.14
     Anſ
    -2.13
    鲞
    -1.91
    )
    -1.88
     ſy
    -1.88
    癰
    -1.83
     sorta
    -1.80
     нѣ
    -1.77
     wasn
    -1.77
    噥
    -1.76
    POSITIVE LOGITS
     and
    2.53
    '
    2.08
     –
    2.00
    All
    1.98
     Since
    1.83
    they
    1.83
     Despite
    1.80
    後
    1.80
     all
    1.77
    on
    1.77
    Act Density 0.000%

    No Known Activations