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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric tokens (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    avy
    -0.08
    assy
    -0.07
    PLICATE
    -0.06
     png
    -0.06
    .icon
    -0.06
    แค
    -0.06
    ítica
    -0.06
    onen
    -0.06
     Duc
    -0.06
     mist
    -0.06
    POSITIVE LOGITS
    募
    0.07
     webpage
    0.07
    TextInput
    0.06
     Cecil
    0.06
     general
    0.06
     graphql
    0.06
    _LINES
    0.06
     ModelAndView
    0.06
    .CustomButton
    0.06
    pageIndex
    0.06
    Act Density 0.015%

    No Known Activations