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

    Neuronpedia

    INDEX
    Explanations

    Option 1 (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이며
    0.73
    while
    0.71
    While
    0.71
     এছাড়াও
    0.69
    এছ
    0.68
    There
    0.68
    !
    0.68
    Примеча
    0.67
     ?
    0.66
    Note
    0.66
    POSITIVE LOGITS
     ≥
    0.87
    "=>
    0.87
     >=
    0.84
     piss
    0.83
    "—
    0.81
    omat
    0.79
    "){
    0.79
     denies
    0.77
    ankton
    0.77
     darn
    0.77
    Act Density 0.343%

    No Known Activations