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

    Neuronpedia

    INDEX
    Explanations

    mechanism or method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dishonesty
    0.41
    也要
    0.41
     också
    0.40
     costruire
    0.40
     scared
    0.40
     unethical
    0.39
     اجمعين
    0.39
    splitContainer
    0.39
     beth
    0.38
     također
    0.38
    POSITIVE LOGITS
    根據
    0.53
    根据
    0.49
    通过
    0.47
     благодаря
    0.47
     according
    0.47
     sayesinde
    0.46
     leveraging
    0.46
     utilizing
    0.45
     باستخدام
    0.45
    凭借
    0.44
    Act Density 0.027%

    No Known Activations