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

    Neuronpedia

    INDEX
    Explanations

    specific numerical representations or symbols, particularly in the context of technical or programming language syntax

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

    acr command group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informant
    -0.48
    enance
    -0.46
    XmlType
    -0.44
    ReusableCell
    -0.44
     egiten
    -0.42
    complexContent
    -0.42
    avigation
    -0.40
     BehaviorSubject
    -0.40
    évaluateur
    -0.40
    VersionUID
    -0.40
    POSITIVE LOGITS
     PartialEq
    0.54
     فريبيس
    0.48
    Према
    0.46
    RTLR
    0.46
     ddelweddau
    0.45
    testify
    0.45
    autoconfigure
    0.45
    Aos
    0.44
    AutoScaleMode
    0.43
     А
    0.42
    Act Density 0.425%

    No Known Activations