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

    Neuronpedia

    INDEX
    Explanations

    requirements.txt files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    0.73
    د
    0.73
    ح
    0.73
    ters
    0.71
    ת
    0.68
    in
    0.67
    ers
    0.64
     that
    0.62
     contraste
    0.59
    ாய
    0.58
    POSITIVE LOGITS
     terrific
    0.59
    ᒎ
    0.58
    原子
    0.57
    ｋ
    0.57
    𝙉
    0.56
    ޏ
    0.56
    ИК
    0.55
    ВА
    0.55
    ｖ
    0.55
    ނ
    0.54
    Act Density 0.003%

    No Known Activations