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

    Neuronpedia

    INDEX
    Explanations

    Moh scales and timeouts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Мі
    0.95
     Allgemeine
    0.93
     Иң
    0.91
    दिग्ध
    0.89
     irritate
    0.89
     obiettivo
    0.89
     Ար
    0.89
    ้
    0.88
     chiuso
    0.88
    ../../
    0.87
    POSITIVE LOGITS
    timeStamp
    0.95
    inho
    0.94
    inning
    0.93
    inou
    0.92
    ono
    0.91
    ående
    0.90
    ontology
    0.89
    isnan
    0.89
    idamente
    0.88
    sdag
    0.88
    Act Density 0.003%

    No Known Activations