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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     captures
    -0.08
     başlad
    -0.08
    capitalize
    -0.08
     Sper
    -0.08
     interventions
    -0.07
    ôm
    -0.07
    captures
    -0.07
    includes
    -0.07
     Georgian
    -0.07
     prednisone
    -0.07
    POSITIVE LOGITS
     প
    0.09
     Bac
    0.09
     الاط
    0.08
     bac
    0.08
     قال
    0.08
     الأص
    0.08
     pap
    0.08
    黒
    0.08
     confirming
    0.08
     المنافس
    0.07
    Act Density 0.001%

    No Known Activations