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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /sw
    -0.07
     comb
    -0.07
     tỏ
    -0.06
    ḻ
    -0.06
    博客
    -0.06
    andWhere
    -0.06
    cljs
    -0.06
     BL
    -0.06
    --;
    -0.06
    )],
    -0.06
    POSITIVE LOGITS
    schüt
    0.08
    率为
    0.08
    lige
    0.07
     الشمال
    0.07
    ationale
    0.07
     overwhelmed
    0.07
     '*
    0.07
    аш
    0.07
    orum
    0.07
    эффект
    0.06
    Act Density 0.001%

    No Known Activations