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

    Neuronpedia

    INDEX
    Explanations

    Random snippets of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gressive
    -0.08
     Turbo
    -0.08
     turbo
    -0.08
    Turbo
    -0.07
     wyk
    -0.07
    Roof
    -0.07
    Expo
    -0.07
    이버
    -0.07
     roof
    -0.07
    /blob
    -0.07
    POSITIVE LOGITS
     belongings
    0.08
     చేస
    0.08
    ოშ
    0.08
     субъект
    0.08
     항상
    0.08
    Mel
    0.07
     bookkeeping
    0.07
    ობლ
    0.07
    ემი
    0.07
     തന്നെ
    0.07
    Act Density 35.543%

    No Known Activations