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

    Neuronpedia

    INDEX
    Explanations

    themes of denial and avoidance in various contexts

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

    denial of truth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Życiorys
    -0.40
    altezza
    -0.37
     ویکی‌پدی
    -0.36
    ufficio
    -0.36
    ClientRect
    -0.36
     braccia
    -0.35
     dikkat
    -0.35
    octanol
    -0.34
     judiciaire
    -0.34
     poissons
    -0.33
    POSITIVE LOGITS
     AssemblyCulture
    0.57
     Italijanski
    0.55
    PostInfinity
    0.54
    XmlIgnore
    0.52
    IsMutable
    0.50
     denial
    0.46
    AnimationsModule
    0.46
     truth
    0.45
    aarrggbb
    0.45
    CppMethod
    0.44
    Act Density 0.081%

    No Known Activations