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

    Neuronpedia

    INDEX
    Explanations

    states/nations

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric tokens containing a decimal point (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Worker
    -0.07
     خانه
    -0.07
     cuer
    -0.07
    	lock
    -0.06
    řejmě
    -0.06
    isayar
    -0.06
    _yield
    -0.06
    (patient
    -0.06
    омен
    -0.06
     pareja
    -0.06
    POSITIVE LOGITS
     Pine
    0.07
     DIY
    0.06
     growing
    0.06
    奈
    0.06
     Brick
    0.06
     jurisdictions
    0.06
     Growing
    0.06
    &W
    0.06
     heb
    0.06
    828
    0.06
    Act Density 0.025%

    No Known Activations