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

    Neuronpedia

    INDEX
    Explanations

    Apache libraries and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Squares
    0.79
     foremost
    0.71
     Bour
    0.71
     digests
    0.70
     Determin
    0.70
    頹
    0.69
     カスタ
    0.68
    ակի
    0.68
     desp
    0.67
    дентифика
    0.67
    POSITIVE LOGITS
    বেল
    0.76
    ঽ
    0.73
    character
    0.71
    adult
    0.70
     प्रार्थना
    0.70
    catal
    0.70
    Tham
    0.70
    log
    0.68
    izem
    0.68
    nation
    0.68
    Act Density 0.000%

    No Known Activations