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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate uncertainty or speculation

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

    expressing possibility or speculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.73
    RenderAtEndOf
    -0.70
    -0.70
    ⪜
    -0.70
    endphp
    -0.69
    IndentedString
    -0.68
    BibitemShut
    -0.66
    -0.66
    <unused8>
    -0.65
    <unused16>
    -0.65
    POSITIVE LOGITS
     Maybe
    0.52
    Maybe
    0.50
     Mungkin
    0.45
    anskje
    0.44
     Apakah
    0.39
     Perhaps
    0.39
    Perhaps
    0.37
     Talvez
    0.36
     Wikiseite
    0.36
     Vielleicht
    0.35
    Act Density 0.035%

    No Known Activations