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

    Neuronpedia

    INDEX
    Explanations

    speed

    np_max-act · gemini-2.0-flash

    This neuron responds to words signaling improved performance or increased levels—especially comparative/superlative terms (e.g. faster, increased, improved).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aira
    -0.07
     placing
    -0.06
     closely
    -0.06
     melan
    -0.06
    Ã
    -0.06
    nist
    -0.06
     důsled
    -0.06
    kin
    -0.06
    	UP
    -0.06
     tennis
    -0.06
    POSITIVE LOGITS
    -days
    0.07
    ルフ
    0.07
    CAT
    0.06
    ώς
    0.06
     Greens
    0.06
     fName
    0.06
    오
    0.06
    ủi
    0.06
    *)
    0.06
    $msg
    0.06
    Act Density 0.027%

    No Known Activations