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

    Neuronpedia

    INDEX
    Explanations

    fragments of code, methods, and configuration details related to programming

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

    to retrieve, during set, can help, will create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.84
    новништво
    -0.78
    XmlAccessType
    -0.74
    AddTagHelper
    -0.73
    ParallelGroup
    -0.71
    expandindo
    -0.70
     ब्रेकडाउन
    -0.70
    enterOuterAlt
    -0.70
     kasarigan
    -0.70
    LookAnd
    -0.70
    POSITIVE LOGITS
    ăzi
    0.34
     Architektur
    0.34
    ktör
    0.33
     modellen
    0.32
    bindet
    0.31
     wrze
    0.30
     desco
    0.30
     Arquitectura
    0.29
    WITH
    0.28
     matéria
    0.28
    Act Density 0.237%

    No Known Activations