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

    Neuronpedia

    INDEX
    Explanations

    names followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incidentally
    0.89
     (
    0.88
     unsur
    0.85
     a
    0.79
     curious
    0.78
     serendip
    0.77
    较为
    0.76
     également
    0.75
     skillful
    0.75
     occasional
    0.74
    POSITIVE LOGITS
    !”,
    1.01
    !!!!
    0.98
    !।
    0.98
    !”.
    0.98
    !`
    0.96
    !",
    0.95
    !-
    0.95
    !!!!!
    0.93
    !!");
    0.93
    !”
    0.93
    Act Density 0.003%

    No Known Activations