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

    Neuronpedia

    INDEX
    Explanations

    way or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.07
    Ad
    0.96
    os
    0.94
    overline
    0.93
    ре
    0.91
    req
    0.91
    و
    0.91
    Adress
    0.90
    م
    0.89
    OS
    0.89
    POSITIVE LOGITS
    ι
    0.87
     দেখেছিলেন
    0.80
     tế
    0.78
     hefty
    0.75
     clave
    0.71
     profundidad
    0.71
    গুলি
    0.70
     fluctu
    0.69
     modo
    0.68
     decisive
    0.67
    Act Density 0.038%

    No Known Activations