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

    Neuronpedia

    INDEX
    Explanations

    hair

    np_max-act · gemini-2.0-flash

    This neuron lights up on numeric tokens representing floating-point values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thigh
    -0.07
    ished
    -0.07
     alive
    -0.06
     گوش
    -0.06
     optimize
    -0.06
    ��
    -0.06
    stim
    -0.06
     hum
    -0.06
    /******/↵
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     boolean
    0.07
     Boolean
    0.06
    _plots
    0.06
    plots
    0.06
     Cyril
    0.06
    	Boolean
    0.06
     Cruiser
    0.06
    Updating
    0.06
    alace
    0.06
    .getConfig
    0.06
    Act Density 0.069%

    No Known Activations