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

    Neuronpedia

    INDEX
    Explanations

    various entities

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially floating‐point or decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     виб
    -0.07
    安装
    -0.07
     mainly
    -0.06
     bunlar
    -0.06
     jiný
    -0.06
     hidden
    -0.06
    ��
    -0.06
     دسته
    -0.06
     medya
    -0.06
     delic
    -0.06
    POSITIVE LOGITS
    居民
    0.07
    кс
    0.06
     Evel
    0.06
     informational
    0.06
     Insets
    0.06
     millionaire
    0.06
     Cliff
    0.06
    izona
    0.06
     Advisor
    0.06
    _COLORS
    0.06
    Act Density 0.228%

    No Known Activations