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

    Neuronpedia

    INDEX
    Explanations

    nan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     performances
    -0.28
    arus
    -0.27
     compromises
    -0.26
     virt
    -0.26
    åħ¬å¹³
    -0.25
    帳
    -0.25
     Boards
    -0.24
    ">&#
    -0.24
     ë¯
    -0.24
    åĮ£
    -0.24
    POSITIVE LOGITS
    .multipart
    0.27
    atically
    0.27
    tem
    0.26
    è¿İ
    0.25
    èĹı
    0.25
    ux
    0.24
    unci
    0.24
    è¡£æľį
    0.24
    çĦĬ
    0.24
    ç©¿ä¸Ĭ
    0.23
    Act Density 0.025%

    No Known Activations