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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric literals (decimal numbers with a fractional part).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Vals
    -0.06
    ',[
    -0.06
     남
    -0.05
     guards
    -0.05
    _:
    -0.05
     bureaucratic
    -0.05
     guard
    -0.05
     Narrow
    -0.05
     Суд
    -0.05
     못
    -0.05
    POSITIVE LOGITS
    ेत
    0.09
     podría
    0.07
    ibal
    0.07
     '"+
    0.07
    _SLOT
    0.07
     OLED
    0.06
    аты
    0.06
     flawless
    0.06
    mouse
    0.06
    fbe
    0.06
    Act Density 0.007%

    No Known Activations