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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing decimal points (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     싱
    -0.06
    vertise
    -0.06
    �除
    -0.06
    Space
    -0.06
    _invalid
    -0.06
     nightlife
    -0.06
    Harness
    -0.06
    ờ
    -0.06
    能力
    -0.06
    .Rest
    -0.06
    POSITIVE LOGITS
    oko
    0.07
    datum
    0.07
    마다
    0.06
    ja
    0.06
     Scar
    0.06
     turns
    0.06
     SCH
    0.06
    ')]
    0.06
     Dr
    0.06
    ايد
    0.06
    Act Density 0.137%

    No Known Activations