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

    Neuronpedia

    INDEX
    Explanations

    identifiers and labeling related to product information

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

    mathematical or code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    errHandler
    -0.40
    AutoScaleMode
    -0.40
    wapV
    -0.37
     obey
    -0.35
     dying
    -0.34
    WithFormat
    -0.34
     wives
    -0.33
    jupiter
    -0.33
     trattano
    -0.33
     suing
    -0.33
    POSITIVE LOGITS
    Buildable
    1.08
     שוליים
    0.75
     Chwiliwch
    0.55
    OGND
    0.53
     queſta
    0.51
     nakalista
    0.50
     estekak
    0.50
    Aholisi
    0.50
    devamını
    0.49
    Tembelea
    0.49
    Act Density 0.000%

    No Known Activations