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

    Neuronpedia

    INDEX
    Explanations

    changes and professional terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aline
    0.80
    zal
    0.77
    över
    0.74
    ชั่น
    0.73
     phosphorylated
    0.72
    alian
    0.71
    onas
    0.71
    ITIONAL
    0.71
    öll
    0.71
     Sá
    0.70
    POSITIVE LOGITS
    مل
    0.85
    н
    0.80
    的确
    0.79
    به
    0.71
    Cron
    0.71
    山
    0.71
    Today
    0.70
    بة
    0.70
    Association
    0.68
    Mountain
    0.67
    Act Density 0.002%

    No Known Activations