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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

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

    "maybe"

    np_acts-logits-general · gemini-2.0-flash

    maybe perhaps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.59
    IContainer
    -0.49
    kmäler
    -0.45
     violation
    -0.45
    CppMethod
    -0.44
    олові
    -0.43
    Билгалдахарш
    -0.43
     Administrativna
    -0.43
    inander
    -0.41
     fuj
    -0.41
    POSITIVE LOGITS
     maybe
    1.67
    Maybe
    1.64
    maybe
    1.63
     Maybe
    1.60
     perhaps
    1.50
    perhaps
    1.50
     Perhaps
    1.44
    Perhaps
    1.41
     quizá
    1.23
     vielleicht
    1.20
    Act Density 0.141%

    No Known Activations