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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and requests for guidance

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

    seeking solutions to problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portály
    -0.63
    esModule
    -0.61
     Wikimedijinoj
    -0.59
     برانيه
    -0.56
     ModelExpression
    -0.55
    extAlignment
    -0.55
     الرياضيه
    -0.55
    Manbalar
    -0.54
    Архівовано
    -0.54
    //});
    -0.53
    POSITIVE LOGITS
    incl
    0.41
     incl
    0.39
    ونج
    0.35
    stag
    0.35
     도
    0.35
    uchen
    0.34
    ugh
    0.34
    ila
    0.33
     مط
    0.32
     plain
    0.32
    Act Density 0.070%

    No Known Activations