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

    Neuronpedia

    INDEX
    Explanations

    elements and attributes in structured data format, such as code or markup languages

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

    Code or data table related tokens

    np_acts-logits-general · gemini-2.0-flash

    code structure and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.77
    msgTypes
    -0.68
     Administrativna
    -0.66
    PyExc
    -0.66
     <=",
    -0.65
     мәкал
    -0.65
     contextLoads
    -0.64
    fjspx
    -0.63
    LookAnd
    -0.63
     ويكيميديا
    -0.63
    POSITIVE LOGITS
     sportifs
    0.32
    ambién
    0.32
    gunas
    0.29
     attributes
    0.29
     atribu
    0.28
     information
    0.28
     rambut
    0.28
     demás
    0.28
     contenido
    0.28
     rense
    0.28
    Act Density 0.219%

    No Known Activations