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

    Neuronpedia

    INDEX
    Explanations

    common denominator

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens representing decimal‐point numbers (floating‐point values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    PARSE
    -0.08
    �은
    -0.07
     bz
    -0.06
    ules
    -0.06
     underline
    -0.06
    achte
    -0.06
    mts
    -0.06
    _lot
    -0.06
     Same
    -0.06
    .carousel
    -0.06
    POSITIVE LOGITS
    	Y
    0.07
    ोल
    0.07
    ErrorMsg
    0.07
    CN
    0.07
     weaknesses
    0.06
     Aussie
    0.06
    教学
    0.06
     Affiliate
    0.06
    帮
    0.06
     디자인
    0.06
    Act Density 0.003%

    No Known Activations