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

    Neuronpedia

    INDEX
    Explanations

    distance and movement

    np_max-act · gemini-2.0-flash

    The neuron primarily 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
     할
    -0.07
     Abdel
    -0.07
     Slater
    -0.07
    bread
    -0.07
     ROAD
    -0.06
     OSX
    -0.06
    geois
    -0.06
     mysqli
    -0.06
    orgetown
    -0.06
     Constr
    -0.06
    POSITIVE LOGITS
    综合
    0.08
    depends
    0.06
     especially
    0.06
    (background
    0.06
     twink
    0.06
     personalize
    0.06
     somehow
    0.06
     directory
    0.06
     shells
    0.06
    unal
    0.06
    Act Density 0.045%

    No Known Activations