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

    Neuronpedia

    INDEX
    Explanations

    Iran, China, Russia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.95
    s
    0.95
    NESS
    0.83
     Fermat
    0.79
     Rhein
    0.76
     berth
    0.76
     Scottish
    0.74
     Städte
    0.74
    ς
    0.73
    Ι
    0.73
    POSITIVE LOGITS
     일
    0.89
    ان
    0.86
    тың
    0.86
    ólicos
    0.85
    odox
    0.83
    acaktır
    0.82
    ствима
    0.82
    ନ
    0.82
     정책
    0.81
    тент
    0.81
    Act Density 0.015%

    No Known Activations