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

    Neuronpedia

    INDEX
    Explanations

    strange creatures and things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لم
    2.17
     puissiez
    2.11
    до
    2.00
    ну
    1.98
    ні
    1.96
    一定的
    1.95
    ર
    1.91
    ри
    1.85
    ⭐
    1.85
    н
    1.84
    POSITIVE LOGITS
    d
    2.20
    t
    1.85
    icrobial
    1.82
    1
    1.82
    p
    1.78
    kings
    1.77
    ently
    1.71
    loads
    1.70
    com
    1.67
    ektedir
    1.67
    Act Density 0.045%

    No Known Activations