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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming and variable management

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

    index and fish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.75
    expandindo
    -0.74
    MLLoader
    -0.72
     queſta
    -0.67
    TagMode
    -0.63
     ſind
    -0.61
     مرئيه
    -0.60
     $_"
    -0.60
    __":
    -0.60
    verifyException
    -0.59
    POSITIVE LOGITS
     con
    0.43
     language
    0.42
     setting
    0.41
    ậc
    0.40
    :
    0.40
     (
    0.40
    ↵↵
    0.40
    性は
    0.39
     "
    0.38
     First
    0.37
    Act Density 0.705%

    No Known Activations