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

    Neuronpedia

    INDEX
    Explanations

    starter kit, starter code, starter player

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Swagger
    0.40
    प्रमुख
    0.40
    パラメータ
    0.39
     swagger
    0.38
     xrange
    0.38
    Pooling
    0.38
    ผ
    0.38
    сько
    0.37
     स्वचालित
    0.37
    Ecommerce
    0.37
    POSITIVE LOGITS
    getParent
    0.41
     bonito
    0.39
     Parent
    0.38
    undert
    0.38
    parent
    0.37
    ⾼
    0.37
    bbs
    0.36
     parent
    0.36
    earth
    0.35
    art
    0.35
    Act Density 0.001%

    No Known Activations