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

    Neuronpedia

    INDEX
    Explanations

    less-than

    np_max-act · gemini-2.0-flash

    The neuron fires on the special markdown-style header lines (the “---” delimiters) that mark off the abstract/metadata blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    来源
    -0.07
     myšlen
    -0.06
    čan
    -0.06
    能源
    -0.06
     anybody
    -0.06
    component
    -0.06
    -0.06
     caregiver
    -0.06
    ANA
    -0.06
    EA
    -0.06
    POSITIVE LOGITS
    aybe
    0.07
     Bond
    0.07
    .isnan
    0.07
    _INITIALIZ
    0.07
    =text
    0.06
     uży
    0.06
    getElementsByTagName
    0.06
    .Res
    0.06
    spin
    0.06
    	FILE
    0.06
    Act Density 0.003%

    No Known Activations