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

    Neuronpedia

    INDEX
    Explanations

    quantitative references and comparisons

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

    and more / etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.65
     CreateTagHelper
    -0.64
    providedIn
    -0.60
     faſt
    -0.58
    AttributeSet
    -0.56
    Edm
    -0.54
    ſelf
    -0.53
    RectangleBorder
    -0.53
    postsleuth
    -0.53
     فريبيس
    -0.52
    POSITIVE LOGITS
     etc
    0.51
    etc
    0.51
    等等
    0.49
     among
    0.43
    等
    0.40
     many
    0.37
     ועוד
    0.37
    他にも
    0.37
     lainnya
    0.36
    意
    0.36
    Act Density 0.281%

    No Known Activations