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

    Neuronpedia

    INDEX
    Explanations

    mentions of leads and advantages in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    winning by margin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.53
    EndProject
    -0.53
    المناصب
    -0.52
    __":
    -0.51
    HomeAsUpEnabled
    -0.50
    Datuak
    -0.50
    EndGlobalSection
    -0.50
    gridx
    -0.49
    windowFixed
    -0.49
    lıkla
    -0.49
    POSITIVE LOGITS
    差
    0.36
    saurus
    0.33
    basedir
    0.33
    Hentet
    0.31
    dpy
    0.30
    kata
    0.30
    Ideal
    0.30
     fortune
    0.30
     gap
    0.29
     Enough
    0.29
    Act Density 0.012%

    No Known Activations