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

    Neuronpedia

    INDEX
    Explanations

    principles

    np_max-act · gemini-2.0-flash

    The neuron is triggered by decimal numbers (floating‐point numerals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     prima
    -0.07
    xsd
    -0.06
    а
    -0.06
    ’↵
    -0.06
    atorio
    -0.06
     decorators
    -0.06
    �
    -0.06
     Glover
    -0.06
    _tools
    -0.06
     satisf
    -0.06
    POSITIVE LOGITS
    juven
    0.07
    :Number
    0.06
     IConfiguration
    0.06
     concentrations
    0.06
    _lahir
    0.06
     müda
    0.06
    .Text
    0.06
    (iOS
    0.06
     ignite
    0.06
     yılında
    0.06
    Act Density 0.105%

    No Known Activations