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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theat
    -0.07
    raq
    -0.06
    NFL
    -0.06
    sterol
    -0.06
    Sanders
    -0.06
     republiky
    -0.06
    Disp
    -0.06
    league
    -0.06
    Cars
    -0.06
    상품
    -0.06
    POSITIVE LOGITS
     五
    0.07
    [^
    0.07
    .…
    0.07
     account
    0.07
     MIDI
    0.06
    味
    0.06
     bal
    0.06
     М
    0.06
    ');↵↵↵↵
    0.06
     bian
    0.06
    Act Density 0.001%

    No Known Activations