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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty or lack of knowledge

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

    negation and lack of knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.57
    原始内容存档于
    -0.56
    󠁣
    -0.50
     ModelExpression
    -0.48
    PasswordEncoder
    -0.47
    Попис
    -0.46
    bootstrapcdn
    -0.46
    PyExc
    -0.46
    webElementXpaths
    -0.45
     bénéfices
    -0.45
    POSITIVE LOGITS
     know
    0.38
     determine
    0.36
     Figuren
    0.35
     Figure
    0.35
     precisely
    0.35
     discul
    0.35
     Wissen
    0.34
    lotz
    0.34
    offline
    0.34
     whether
    0.34
    Act Density 0.057%

    No Known Activations