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

    Neuronpedia

    INDEX
    Explanations

    claimscenarioMarchtwowhatrekindNo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intérieure
    0.94
    ющий
    0.91
    ेन्द्र
    0.88
    鸚
    0.87
    ições
    0.86
    میں
    0.84
     nghỉ
    0.84
    ческие
    0.80
     mögliche
    0.80
     zweite
    0.79
    POSITIVE LOGITS
    (
    0.78
     dealings
    0.71
    {
    0.71
    :
    0.67
        
    0.66
    الصفحه
    0.66
    }}:=\
    0.66
    Modulo
    0.65
     decis
    0.64
    academy
    0.64
    Act Density 0.000%

    No Known Activations