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

    Neuronpedia

    INDEX
    Explanations

    comments and documentation in code

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

    text starting with user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.61
    Diwedd
    -0.54
     صوتيه
    -0.51
    MessageOf
    -0.50
    inSlope
    -0.49
    LookAnd
    -0.49
    tinyos
    -0.47
     Administrativna
    -0.47
     للاسماء
    -0.47
    oredCriteria
    -0.47
    POSITIVE LOGITS
    awtextra
    0.43
     Trock
    0.42
     Falls
    0.41
    rta
    0.41
     Fonseca
    0.40
     Campos
    0.40
    Campo
    0.40
     Gutes
    0.40
    riger
    0.39
    erder
    0.39
    Act Density 0.016%

    No Known Activations