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

    Neuronpedia

    INDEX
    Explanations

    python ml libraries installation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -,
    0.72
    ence
    0.72
    éis
    0.72
    imate
    0.70
    épaisseur
    0.69
    humidité
    0.69
    assurance
    0.68
    $-
    0.68
    ierz
    0.67
    ió
    0.67
    POSITIVE LOGITS
     וש
    0.79
     MongoDB
    0.76
    复制代码
    0.75
     }}
    0.74
     उर्फ
    0.72
     Wish
    0.72
     groupBy
    0.72
    之类的
    0.71
     vostro
    0.70
     datetime
    0.70
    Act Density 0.030%

    No Known Activations