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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beispiel
    -0.07
    ність
    -0.06
     кал
    -0.06
    leness
    -0.06
     Interested
    -0.06
     ป
    -0.06
    ापन
    -0.06
     thai
    -0.06
    Closed
    -0.06
     необходим
    -0.06
    POSITIVE LOGITS
     Dur
    0.07
     Stripe
    0.06
    nim
    0.06
    0.06
     článek
    0.06
     tok
    0.06
     Ryan
    0.06
    _pll
    0.06
     Esc
    0.06
     idols
    0.06
    Act Density 0.010%

    No Known Activations