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

    Neuronpedia

    INDEX
    Explanations

    code, headings, and formatting markup

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imedia
    -0.56
    /}{
    -0.50
     án
    -0.47
    imir
    -0.46
     thế
    -0.46
    }{
    -0.45
     w
    -0.44
    /*!
    -0.44
    EIN
    -0.44
     !=
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.79
     Theſe
    0.77
    localctx
    0.75
    StoryboardSegue
    0.72
    expandindo
    0.65
    +#+
    0.65
    Tembelea
    0.63
     Efq
    0.62
    AsUp
    0.61
     autorytatywna
    0.57
    Act Density 2.536%

    No Known Activations