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

    Neuronpedia

    INDEX
    Explanations

    CONFIG

    np_max-act · gemini-2.0-flash

    The neuron fires on build‐configuration macro names (tokens like “CONFIG_*”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     payroll
    -0.08
     peptide
    -0.07
     goals
    -0.07
     Mile
    -0.07
     intimidate
    -0.07
     towers
    -0.07
     murdered
    -0.07
    ierarchy
    -0.07
     daycare
    -0.06
     Able
    -0.06
    POSITIVE LOGITS
    .phi
    0.06
     BOOL
    0.06
    RESSION
    0.06
    _configure
    0.06
    	Config
    0.06
     OMX
    0.06
    ,lat
    0.06
     unp
    0.06
     вк
    0.06
     CONFIG
    0.05
    Act Density 0.001%

    No Known Activations