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

    Neuronpedia

    INDEX
    Explanations

    languages and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    2.46
    s
    1.82
    T
    1.69
    RU
    1.64
    𝘻
    1.63
    ы
    1.58
    ים
    1.57
     interrog
    1.51
     strata
    1.48
    ের
    1.47
    POSITIVE LOGITS
     불구하고
    1.82
    服务端
    1.67
    editText
    1.64
     Rounded
    1.60
     callSettings
    1.53
    िक
    1.51
    হ্যালো
    1.49
     PROFITS
    1.47
    రిత్ర
    1.46
    اسم
    1.45
    Act Density 0.000%

    No Known Activations