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

    Neuronpedia

    INDEX
    Explanations

    references to error handling in code

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

    error checking in code sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Accumulator
    -0.38
    Mixin
    -0.36
    ModelAttribute
    -0.35
    drawSprites
    -0.35
    以
    -0.33
     Kader
    -0.32
    kad
    -0.31
     AssemblyTitle
    -0.31
    ETERS
    -0.30
    efficacité
    -0.30
    POSITIVE LOGITS
    +#+#
    0.75
     defaultstate
    0.73
    SharedDtor
    0.70
    parsedMessage
    0.67
    awtextra
    0.63
     autorytatywna
    0.60
     ModelExpression
    0.58
    MemoryWarning
    0.56
    IntoConstraints
    0.56
    SequentialGroup
    0.56
    Act Density 0.036%

    No Known Activations