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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash

    code structure and elements related to template messages in a programming context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on tokens that are numeric (i.e. contain digits), such as version numbers, counts, IDs, or other number strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     regulating
    -0.07
    enerative
    -0.06
    _Static
    -0.06
    人が
    -0.06
     tokenize
    -0.06
    applicant
    -0.06
     colonies
    -0.06
    랍니다
    -0.06
    iedade
    -0.06
    dto
    -0.06
    POSITIVE LOGITS
    :ss
    0.07
     iz
    0.07
     Persona
    0.06
     Session
    0.06
    عل
    0.06
     Uni
    0.06
    FormItem
    0.06
     stays
    0.06
     /*#__
    0.06
    ülen
    0.06
    Act Density 0.008%

    No Known Activations