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

    Neuronpedia

    INDEX
    Explanations

    code snippets including parentheses and certain symbols

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.86
    ,
    -0.76
    ↵↵
    -0.74
     the
    -0.73
     
    -0.69
    !
    -0.69
     a
    -0.67
    -
    -0.67
    ↵
    -0.64
    <eos>
    -0.62
    POSITIVE LOGITS
     AssemblyCulture
    1.38
     propOrder
    1.35
     للمعارف
    1.34
    ThroughAttribute
    1.34
    AddTagHelper
    1.31
     المعيارى
    1.28
    ConstraintMaker
    1.27
    IntoConstraints
    1.26
    RenderAtEndOf
    1.24
    endphp
    1.23
    Act Density 0.959%

    No Known Activations