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

    Neuronpedia

    INDEX
    Explanations

    syntax of parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ihe
    0.97
    ꯟ
    0.89
    ᱙
    0.85
     cuk
    0.83
     dự
    0.82
    jdk
    0.82
     verbess
    0.81
    біць
    0.80
     Scotty
    0.80
     açúcar
    0.79
    POSITIVE LOGITS
    AN
    0.80
    ENT
    0.79
     Cited
    0.76
    이트
    0.74
     Π
    0.73
    MAN
    0.70
     diligence
    0.70
    న్
    0.68
    ِن
    0.67
    Globalization
    0.67
    Act Density 0.000%

    No Known Activations