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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     실제
    -0.06
     yaş
    -0.06
    encial
    -0.06
    不同的
    -0.06
    nob
    -0.06
     retains
    -0.06
     println
    -0.06
     nuts
    -0.06
     sacr
    -0.06
    因
    -0.06
    POSITIVE LOGITS
     рег
    0.06
     Henrik
    0.06
    Dialog
    0.06
    ат
    0.06
    体育
    0.06
    >Email
    0.06
    で
    0.06
    ModelIndex
    0.06
    <Point
    0.06
     doprav
    0.06
    Act Density 0.000%

    No Known Activations