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

    Neuronpedia

    INDEX
    Explanations

    importance and cruciality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Möglichkeiten
    0.59
     Schwier
    0.53
    ación
    0.48
    smöglichkeiten
    0.48
    सँग
    0.47
     лучших
    0.47
     cánh
    0.46
    ა
    0.45
    স্র
    0.45
     capaz
    0.44
    POSITIVE LOGITS
     important
    0.98
     importants
    0.95
     importante
    0.95
     penting
    0.95
    important
    0.90
     importance
    0.89
     важ
    0.89
     importantes
    0.87
    Important
    0.85
     Important
    0.84
    Act Density 0.265%

    No Known Activations