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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bl
    -0.07
    .ci
    -0.06
     Мик
    -0.06
    師
    -0.06
    -dark
    -0.06
    ниц
    -0.06
    :t
    -0.06
    нож
    -0.06
    Tanggal
    -0.06
     mountains
    -0.06
    POSITIVE LOGITS
     خوش
    0.07
     зак
    0.07
    .HttpServletResponse
    0.07
    росто
    0.07
    60
    0.07
    race
    0.07
    960
    0.07
    UMENT
    0.06
    ردد
    0.06
    пп
    0.06
    Act Density 0.001%

    No Known Activations