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

    Neuronpedia

    INDEX
    Explanations

    issues and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.56
    8
    0.52
     appelée
    0.51
     используется
    0.49
    4
    0.49
    s
    0.48
    不错的
    0.48
    5
    0.47
    t
    0.47
    yó
    0.46
    POSITIVE LOGITS
    ᅬ
    0.43
     UNI
    0.43
     minority
    0.42
     تغییر
    0.41
     سنه
    0.40
    ोगी
    0.39
    ργ
    0.39
     fract
    0.39
     серь
    0.39
    ੍ਰ
    0.39
    Act Density 0.000%

    No Known Activations