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

    Neuronpedia

    INDEX
    Explanations

    concepts and clarifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hegemony
    0.42
    ânico
    0.41
    RELAND
    0.41
     Bestellung
    0.41
    徸
    0.41
     parametros
    0.40
    AYLOR
    0.40
    ATIV
    0.40
     blatantly
    0.40
     refinance
    0.39
    POSITIVE LOGITS
    ܬ
    0.41
     Vide
    0.41
    ت
    0.40
     recited
    0.40
    Vide
    0.40
    ကာ
    0.38
    pads
    0.38
     Sor
    0.38
    تب
    0.37
    عي
    0.36
    Act Density 0.001%

    No Known Activations