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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting instructions in a structured data context

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

    code assignments and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.80
     pleaſure
    -0.69
     ModelExpression
    -0.67
    bootstrapcdn
    -0.65
    writeFieldEnd
    -0.63
    ſelves
    -0.61
    новништво
    -0.59
    ſelf
    -0.59
     queſta
    -0.59
     дописавши
    -0.56
    POSITIVE LOGITS
    lys
    0.45
     adel
    0.44
     extra
    0.43
     논
    0.41
    je
    0.41
    Extra
    0.41
    cjonal
    0.41
    ito
    0.40
    replaceAll
    0.40
    2
    0.40
    Act Density 0.030%

    No Known Activations