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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, especially decimal numbers (floating-point values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fondo
    -0.07
    ODY
    -0.07
    ody
    -0.07
     их
    -0.07
    /GPL
    -0.07
    .tr
    -0.07
    Vis
    -0.06
    -ie
    -0.06
    obierno
    -0.06
    _feedback
    -0.06
    POSITIVE LOGITS
    urious
    0.06
     signage
    0.06
    erts
    0.06
    .UserService
    0.06
     उनक
    0.06
     lim
    0.06
     Symphony
    0.06
    (dynamic
    0.06
     Meeting
    0.06
     rendered
    0.06
    Act Density 0.019%

    No Known Activations