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

    Neuronpedia

    INDEX
    Explanations

    HTML comment tags

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

    HTML comments

    np_acts-logits-general · gemini-2.0-flash

    <!-- comments -->

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.92
    brainly
    -0.82
    fillType
    -0.79
    fromUtf
    -0.76
     tph
    -0.73
     Архів
    -0.71
    LookAnd
    -0.71
    AsUp
    -0.71
    : 
    -0.70
    原始内容存档于
    -0.69
    POSITIVE LOGITS
    <!--
    1.34
    ><!--
    1.19
     <!--
    1.08
    "><!--
    1.05
     يتيمه
    0.69
     -->
    0.66
     saddles
    0.66
     Middles
    0.65
     McIl
    0.64
     leaſt
    0.63
    Act Density 0.090%

    No Known Activations