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

    Neuronpedia

    INDEX
    Explanations

    terms related to changes, studies, or reports

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

    section headings and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dieſer
    -0.60
    ulongan
    -0.59
     ſein
    -0.53
    Uniform
    -0.52
     beſte
    -0.50
     AssemblyTitle
    -0.50
     ſelbſt
    -0.50
     ویکی‌پدی
    -0.50
     dieſe
    -0.49
    Conclusie
    -0.49
    POSITIVE LOGITS
     surla
    0.45
    stdc
    0.45
    IContainer
    0.36
     ffilmiau
    0.36
    但他
    0.36
    >")
    0.35
    logrus
    0.34
    Diweddarwch
    0.34
    benar
    0.33
    HttpFoundation
    0.33
    Act Density 0.224%

    No Known Activations