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

    Neuronpedia

    INDEX
    Explanations

    when/where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     with
    -0.51
     so
    -0.50
     such
    -0.48
     оригіналу
    -0.48
     then
    -0.47
    Ÿ
    -0.47
    typedef
    -0.47
     I
    -0.46
    zość
    -0.46
     Then
    -0.45
    POSITIVE LOGITS
    ;">
    0.67
    />";
    0.65
    )++;
    0.64
    '>
    0.64
    InputTagHelper
    0.63
    >';
    0.61
     '))
    0.61
     ';
    0.60
    '));
    0.60
    ISupport
    0.60
    Act Density 0.003%

    No Known Activations