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

    Neuronpedia

    INDEX
    Explanations

    technical or code-related elements, particularly in programming or markup languages

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

    LaTeX formatting with math, code, or markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ApiModelProperty
    -0.34
     encar
    -0.32
     dimenti
    -0.32
    PropertyValue
    -0.32
    parametrize
    -0.31
    ływ
    -0.31
     olvides
    -0.31
    PathVariable
    -0.30
     Privat
    -0.30
     appropriate
    -0.30
    POSITIVE LOGITS
    sizeCache
    0.70
     surla
    0.64
    MLLoader
    0.59
    BufferException
    0.56
     EconPapers
    0.56
     ModelExpression
    0.56
    unknownFields
    0.54
    qtype
    0.53
    GeneratedCode
    0.53
     defaultstate
    0.52
    Act Density 0.003%

    No Known Activations