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

    Neuronpedia

    INDEX
    Explanations

    necessary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strongly
    -0.07
    Larry
    -0.07
     closure
    -0.07
     graphical
    -0.07
     blank
    -0.07
     critical
    -0.07
     convenience
    -0.07
     Larry
    -0.07
     sy
    -0.07
     effectively
    -0.07
    POSITIVE LOGITS
     മലയാള
    0.09
     নির্বাচ
    0.08
     [])↵
    0.08
     merveille
    0.08
    상품
    0.08
     বঙ্গবন্ধ
    0.08
    িয
    0.08
    מבר
    0.08
     [...
    0.08
     []);↵↵
    0.08
    Act Density 0.002%

    No Known Activations