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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—integers, decimals, fractions, and signed numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Garrett
    -0.07
    _PARAM
    -0.06
     Kı
    -0.06
    _CAT
    -0.06
    ".↵↵
    -0.06
    prefer
    -0.06
    -family
    -0.06
     password
    -0.06
     Incredible
    -0.06
     食
    -0.06
    POSITIVE LOGITS
     eliminated
    0.06
    patible
    0.06
    -article
    0.06
     переда
    0.06
     Beta
    0.06
    تس
    0.06
     внес
    0.06
    yle
    0.06
    .norm
    0.06
    -interface
    0.06
    Act Density 0.005%

    No Known Activations