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

    Neuronpedia

    INDEX
    Explanations

    responses related to uncertainty or difficulty in remembering specific details

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

    Requests for precision or confirmation

    np_acts-logits-general · gemini-2.0-flash

    exactness and specificity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.63
    WebServlet
    -0.55
    érience
    -0.54
     مشين
    -0.52
    UrlResolution
    -0.52
     فريبيس
    -0.52
    +#+#
    -0.50
    EndInit
    -0.49
    الإنجليزية
    -0.49
    fromCharCode
    -0.48
    POSITIVE LOGITS
     exact
    3.25
     exactly
    3.03
    exact
    2.83
    exactly
    2.73
     Exact
    2.63
     precisely
    2.61
     Exactly
    2.58
    precise
    2.56
    Exact
    2.51
     precise
    2.50
    Act Density 0.713%

    No Known Activations