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

    Neuronpedia

    INDEX
    Explanations

    warranty claims and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.80
    上半
    0.76
    もので
    0.75
     cyclohex
    0.73
    。,
    0.72
    ۔
    0.72
     ⿱
    0.71
    。《
    0.71
     pagoda
    0.70
     สําหรับ
    0.69
    POSITIVE LOGITS
    Warranty
    1.09
    ти
    0.95
     warranties
    0.92
    warranty
    0.89
    ת
    0.88
     Warranty
    0.87
     (
    0.86
    ↵
    0.84
    Type
    0.84
    0
    0.82
    Act Density 0.003%

    No Known Activations