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

    Neuronpedia

    INDEX
    Explanations

    scientific experiments and measurements

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (digits and numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Page
    -0.08
     Panther
    -0.07
    iare
    -0.07
     مربع
    -0.07
    .Car
    -0.06
    ome
    -0.06
     Lady
    -0.06
     licz
    -0.06
    .Manifest
    -0.06
     cob
    -0.06
    POSITIVE LOGITS
    =pd
    0.07
    [event
    0.07
     squeezing
    0.06
    xo
    0.06
    CastException
    0.06
     opsiyon
    0.06
     pasar
    0.06
     ğ
    0.06
    ']=$
    0.06
     scrutiny
    0.06
    Act Density 0.024%

    No Known Activations