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

    Neuronpedia

    INDEX
    Explanations

    conversion to integer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sensibilité
    0.42
    ógł
    0.39
    ეთი
    0.38
     języ
    0.38
     اللغة
    0.38
     เอก
    0.38
     Resmi
    0.38
    ServiceName
    0.38
    感情
    0.37
    consciousness
    0.37
    POSITIVE LOGITS
     promedio
    0.38
     October
    0.38
     gar
    0.37
     циф
    0.37
     thermometers
    0.36
     تب
    0.36
     छूट
    0.36
     пр
    0.36
     Bono
    0.36
     Jefferson
    0.36
    Act Density 0.033%

    No Known Activations