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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to filtering and manipulating data in programming contexts

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

    filter by position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.57
     BoxDecoration
    -0.56
    UrlResolution
    -0.55
    withIdentifier
    -0.54
     iprot
    -0.53
    AndEndTag
    -0.52
    cerpt
    -0.50
    AddHtmlAttribute
    -0.49
    -0.49
    RegistryLite
    -0.47
    POSITIVE LOGITS
    исленность
    0.36
     elástica
    0.34
    PropertyChanging
    0.34
    Personensuche
    0.34
     filters
    0.34
    šanai
    0.34
     piemē
    0.33
     filtered
    0.33
     filter
    0.33
     oculto
    0.32
    Act Density 0.009%

    No Known Activations