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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (especially floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mill
    -0.07
     Purpose
    -0.06
    _con
    -0.06
    孩子
    -0.06
     Recognition
    -0.06
     〃
    -0.06
     [:
    -0.06
     Funk
    -0.06
     Trilogy
    -0.06
    therapy
    -0.06
    POSITIVE LOGITS
     цін
    0.07
    _TD
    0.07
     uncomment
    0.07
     τό
    0.06
    .form
    0.06
     adı
    0.06
     бенз
    0.06
    elsif
    0.06
     backward
    0.06
    ……」↵↵
    0.06
    Act Density 0.189%

    No Known Activations