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

    Neuronpedia

    INDEX
    Explanations

    solution to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tiered
    0.63
    enteric
    0.61
    த்தூர்
    0.60
    paddle
    0.60
     hom
    0.59
     latitudes
    0.59
    enters
    0.58
     tiered
    0.57
     exuber
    0.57
    ース
    0.56
    POSITIVE LOGITS
     ofthe
    1.23
     of
    1.20
     của
    1.18
     của
    1.13
    ของ
    1.04
    ของการ
    0.99
    OfThe
    0.97
     של
    0.95
     tohoto
    0.89
     цього
    0.87
    Act Density 0.566%

    No Known Activations