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

    Neuronpedia

    INDEX
    Explanations

    terms related to backend processing and data structure in programming

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

    Preceding a slash or a colon

    np_acts-logits-general · gemini-2.0-flash

    file paths and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mergeFrom
    -1.14
     ModelExpression
    -1.06
    SourceChecksum
    -1.06
     Roskov
    -1.05
     &___
    -1.04
    LookAnd
    -0.97
    новниш
    -0.94
     >=",
    -0.90
    AddTagHelper
    -0.89
    ']")
    -0.87
    POSITIVE LOGITS
    .
    0.62
    ,
    0.50
    core
    0.42
    :
    0.41
    /
    0.38
     gidi
    0.38
     însă
    0.37
    Handlung
    0.35
    HideInInspector
    0.35
     principle
    0.35
    Act Density 0.169%

    No Known Activations