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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spotify
    -0.07
    .Reverse
    -0.07
    Buzz
    -0.06
     Baylor
    -0.06
     Roger
    -0.06
    ague
    -0.06
     cage
    -0.06
    dispatch
    -0.06
    Physics
    -0.06
     Prince
    -0.06
    POSITIVE LOGITS
    <SpriteRenderer
    0.07
    isiert
    0.06
    σι
    0.06
    ehir
    0.06
     ओ
    0.06
     дити
    0.06
     Müslüman
    0.06
    -----------
↵
    0.06
     Май
    0.06
    $tpl
    0.06
    Act Density 0.036%

    No Known Activations