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

    Neuronpedia

    INDEX
    Explanations

    function and method declaration syntax in programming languages

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

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.82
    principalColumn
    -0.60
     resourceCulture
    -0.53
     yyr
    -0.53
     HttpNotFound
    -0.52
    __*/
    -0.52
     defaultstate
    -0.50
    -0.50
     виправивши
    -0.48
    windowFixed
    -0.48
    POSITIVE LOGITS
    SPATH
    0.40
     Acerca
    0.37
    difference
    0.35
     embarc
    0.35
    تفصیلات
    0.35
     difference
    0.35
     Flanders
    0.34
     rajut
    0.34
     elettrico
    0.34
     Bedienung
    0.34
    Act Density 0.034%

    No Known Activations