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

    Neuronpedia

    INDEX
    Explanations

    new beginnings or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    proces
    0.44
    ื
    0.40
     ሀ
    0.39
    quit
    0.38
    video
    0.38
    オー
    0.38
     ममता
    0.38
    fully
    0.38
    header
    0.38
     हिंदी
    0.37
    POSITIVE LOGITS
     nuevos
    0.46
     nuovi
    0.46
     nových
    0.44
     nuova
    0.42
     sistemi
    0.40
    新たな
    0.40
     nouveaux
    0.40
     nový
    0.40
     erk
    0.39
     novos
    0.38
    Act Density 0.000%

    No Known Activations