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

    Neuronpedia

    INDEX
    Explanations

    urls and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     huj
    0.72
     ሴ
    0.68
    Spart
    0.67
     Hob
    0.66
     talon
    0.66
     hipster
    0.65
    ক্তার
    0.64
    lení
    0.64
    tenant
    0.64
     tibia
    0.63
    POSITIVE LOGITS
     baş
    0.64
    cook
    0.64
     конвер
    0.64
     contrário
    0.62
     Cook
    0.62
    สัง
    0.62
    処
    0.60
    COOK
    0.59
    寅
    0.58
    Cook
    0.57
    Act Density 0.007%

    No Known Activations