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

    Neuronpedia

    INDEX
    Explanations

    Memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skilled
    -0.08
     fortunate
    -0.08
     joyous
    -0.07
    luck
    -0.07
    نعة
    -0.07
     lombok
    -0.07
    -skilled
    -0.07
    大众
    -0.07
    Delimiter
    -0.07
     desenhos
    -0.07
    POSITIVE LOGITS
     יום
    0.09
     午
    0.08
    .imshow
    0.08
    Wilt
    0.08
     ориент
    0.08
     上午
    0.08
     متاثر
    0.08
    午
    0.08
     verstre
    0.08
     органов
    0.07
    Act Density 0.000%

    No Known Activations