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

    Neuronpedia

    INDEX
    Explanations

    lots of

    np_max-act · gemini-2.0-flash

    This neuron responds to intensive quantifier phrases—words that emphasize large amounts (e.g. “lots,” “lots of,” “detail”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mask
    -0.06
     bag
    -0.06
     Brad
    -0.06
    еса
    -0.05
    bp
    -0.05
     Owl
    -0.05
     गय
    -0.05
    Fuel
    -0.05
     Ow
    -0.05
    hit
    -0.05
    POSITIVE LOGITS
    UGHT
    0.08
    บรร
    0.08
    ایسه
    0.08
    ahrenheit
    0.07
    !(
    0.07
     attitudes
    0.07
    rió
    0.07
    obbies
    0.07
     meses
    0.07
     생활
    0.07
    Act Density 0.001%

    No Known Activations