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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens representing floating-point number literals (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     POWER
    -0.07
     Featuring
    -0.06
    Markdown
    -0.06
    _Menu
    -0.06
    acios
    -0.06
     inode
    -0.06
     undergraduate
    -0.06
     Wang
    -0.06
    ']}
    -0.06
     ctl
    -0.06
    POSITIVE LOGITS
    ([])↵
    0.07
     vůbec
    0.07
    .isSuccess
    0.07
    ournal
    0.06
    ，然后
    0.06
    _pixels
    0.06
     erase
    0.06
    Ubergraph
    0.06
     phía
    0.06
     başar
    0.06
    Act Density 0.281%

    No Known Activations