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

    Neuronpedia

    INDEX
    Explanations

    Demonstrative pronouns

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens containing decimal points, i.e., floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     webhook
    -0.07
    \Requests
    -0.07
     Collapse
    -0.07
     impro
    -0.06
    requete
    -0.06
    lilik
    -0.06
     Е
    -0.06
     keyof
    -0.06
     worst
    -0.06
     {});↵
    -0.06
    POSITIVE LOGITS
     Jug
    0.07
    _bi
    0.07
     δι
    0.07
     Dre
    0.07
     encounter
    0.07
    着
    0.06
    /terms
    0.06
    人民
    0.06
    zerbai
    0.06
    .ec
    0.06
    Act Density 0.006%

    No Known Activations