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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any of the tokens shown—it remains inactive (a “dead” neuron) on all of these inputs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Show
    -0.07
    (Util
    -0.07
    awks
    -0.07
    !/
    -0.07
     fingert
    -0.06
    Inlining
    -0.06
     wxDefault
    -0.06
     lodge
    -0.06
     incentives
    -0.06
     ///</
    -0.06
    POSITIVE LOGITS
     pron
    0.06
     Společ
    0.06
    _ta
    0.06
    oolStrip
    0.06
     тур
    0.06
     olig
    0.06
    люч
    0.06
    ToDo
    0.06
    _correct
    0.06
     tabindex
    0.06
    Act Density 0.014%

    No Known Activations