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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to programming and model loading in machine learning

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

    Tokens before numbers

    np_acts-logits-general · gemini-2.0-flash

    and verification or genetic record

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brooks
    -0.36
     thread
    -0.36
    ợ
    -0.34
     Schen
    -0.34
     Oppen
    -0.34
    thread
    -0.33
     construction
    -0.33
     Wille
    -0.32
    anchor
    -0.32
     Renaud
    -0.31
    POSITIVE LOGITS
    AndEndTag
    0.66
     المعيارى
    0.64
    SourceChecksum
    0.62
     classifying
    0.60
    الحياه
    0.60
    TagMode
    0.59
    IBOutlet
    0.57
     bluzka
    0.55
     Roskov
    0.55
    httphttps
    0.54
    Act Density 0.203%

    No Known Activations