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

    Neuronpedia

    INDEX
    Explanations

    lots

    np_max-act · gemini-2.0-flash

    This neuron fires on vague quantity expressions—words like “lots,” “heaps,” and similar non-numeric quantifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Invalidate
    -0.07
    ію
    -0.07
     agre
    -0.07
     hạ
    -0.07
    _record
    -0.07
    обрет
    -0.06
     Petro
    -0.06
    ображ
    -0.06
     Beled
    -0.06
    imeter
    -0.06
    POSITIVE LOGITS
     lots
    0.10
    Lots
    0.09
    .S
    0.08
     Lots
    0.08
    TS
    0.08
     JS
    0.07
    PS
    0.07
    ts
    0.07
    OTS
    0.07
    -ts
    0.07
    Act Density 0.008%

    No Known Activations