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

    Neuronpedia

    INDEX
    Explanations

    lists and numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on fragments of floating‐point numeric values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    DWORD
    -0.07
     ocean
    -0.07
    full
    -0.06
    (adj
    -0.06
    詳細
    -0.06
     string
    -0.06
    .smtp
    -0.06
    _INTEGER
    -0.06
     minWidth
    -0.06
     rare
    -0.06
    POSITIVE LOGITS
     Sark
    0.07
     laying
    0.06
     iddia
    0.06
     keyof
    0.06
    )').
    0.06
     устра
    0.06
    炎
    0.06
    ฆ
    0.06
     beled
    0.06
    แชม
    0.06
    Act Density 0.338%

    No Known Activations