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

    Neuronpedia

    INDEX
    Explanations

    Percentages

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical statistical values (e.g., percentages, survival‐rate figures, p-values) reported in study results.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cone
    -0.06
    』↵↵
    -0.06
    γι
    -0.06
     그는
    -0.06
    097
    -0.06
     Porsche
    -0.06
    744
    -0.06
     cade
    -0.06
    -й
    -0.06
     ﾍ
    -0.05
    POSITIVE LOGITS
    .Arrays
    0.07
     hashmap
    0.07
    äm
    0.07
    记
    0.06
    _ENV
    0.06
     Yorkshire
    0.06
    _hyper
    0.06
    �
    0.06
     wins
    0.06
    /dev
    0.06
    Act Density 0.026%

    No Known Activations