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

    Neuronpedia

    INDEX
    Explanations

    observation

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical measurement values (especially decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    unuz
    -0.06
    bio
    -0.06
    OSE
    -0.06
     going
    -0.06
    Info
    -0.06
    avors
    -0.06
    Enemy
    -0.06
    Like
    -0.06
     Chí
    -0.06
    *math
    -0.06
    POSITIVE LOGITS
     shiny
    0.07
    _bw
    0.07
    KB
    0.06
    _cpus
    0.06
    Mbps
    0.06
    ，存于
    0.06
     AMS
    0.06
     ETA
    0.06
    %");↵
    0.06
     uri
    0.06
    Act Density 0.039%

    No Known Activations