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

    Neuronpedia

    INDEX
    Explanations

    code or data

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—specifically on numbers in lists or sequences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gallery
    -0.06
     ctx
    -0.06
     arena
    -0.06
    eos
    -0.06
     organization
    -0.06
     crafted
    -0.06
    _r
    -0.06
     considering
    -0.06
    .Xaml
    -0.06
     riding
    -0.05
    POSITIVE LOGITS
    �
    0.08
    ysz
    0.08
     swingers
    0.07
     unb
    0.07
    (MenuItem
    0.06
    (SDL
    0.06
     Naomi
    0.06
     Aless
    0.06
     Yosemite
    0.06
     Hiç
    0.06
    Act Density 0.006%

    No Known Activations