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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing precise decimal values (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ?type
    -0.07
     Т
    -0.07
    AntiForgeryToken
    -0.07
    ..........
    -0.06
    ̀
    -0.06
     apiKey
    -0.06
    Identifier
    -0.06
     Harlem
    -0.06
     garant
    -0.06
     electricity
    -0.06
    POSITIVE LOGITS
    Ess
    0.07
    вав
    0.07
    	rb
    0.07
    .Xr
    0.06
    HITE
    0.06
    scalar
    0.06
    (argc
    0.06
    headers
    0.06
    慌
    0.06
     ngOnDestroy
    0.06
    Act Density 0.068%

    No Known Activations