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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated mathematical expressions

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

    scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelRenderer
    -0.31
    }{*}{}
    -0.30
     lizenzfreies
    -0.29
    "/",
    -0.29
     spéc
    -0.29
     chapters
    -0.29
    发表于
    -0.28
     nôtre
    -0.28
     whether
    -0.28
    構
    -0.27
    POSITIVE LOGITS
    ValueStyle
    0.82
    HostException
    0.69
    SBATCH
    0.66
    ConstraintMaker
    0.66
    nanoTime
    0.64
    Cyfarwyddwr
    0.63
    makeText
    0.62
    arraycopy
    0.62
    TargetException
    0.59
     становника
    0.58
    Act Density 0.034%

    No Known Activations