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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slaves
    0.77
     দখল
    0.75
     commemorating
    0.72
    <unused566>
    0.71
    ଥି
    0.71
    리카
    0.70
    ClearedBy
    0.70
     ادارے
    0.70
     થી
    0.70
     disables
    0.70
    POSITIVE LOGITS
    ෝ
    0.63
     ++;
    0.61
    haba
    0.61
    hame
    0.61
    नाडा
    0.60
    protobuf
    0.60
    language
    0.60
    IDENTITY
    0.59
     predic
    0.59
    htein
    0.58
    Act Density 0.009%

    No Known Activations