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

    Neuronpedia

    INDEX
    Explanations

    FastAPI instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.99
    el
    0.78
     вышла
    0.75
    u
    0.75
     Watson
    0.73
    er
    0.72
    orar
    0.72
     Cameron
    0.71
     восто
    0.71
    sa
    0.70
    POSITIVE LOGITS
     réflex
    0.84
     proteine
    0.82
    គ្
    0.79
    アイドル
    0.78
    職
    0.76
     diarrh
    0.72
     impotence
    0.71
     lawe
    0.71
    ابد
    0.70
     probablement
    0.70
    Act Density 0.006%

    No Known Activations