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

    Neuronpedia

    INDEX
    Explanations

    bandwidth and signal processing

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric measurement values (floating‐point numbers) in technical contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pedestal
    -0.07
     infection
    -0.07
    "As
    -0.07
    ")).
    -0.07
     predomin
    -0.06
     ushort
    -0.06
     JM
    -0.06
    Mana
    -0.06
    “As
    -0.06
     Eduardo
    -0.06
    POSITIVE LOGITS
     willing
    0.06
    روت
    0.06
     defined
    0.06
    music
    0.06
     클
    0.06
    们
    0.06
     ruh
    0.06
    ाहरण
    0.06
     trickle
    0.06
     सन
    0.06
    Act Density 0.006%

    No Known Activations