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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    folder
    -0.07
    ُر
    -0.07
    .Scene
    -0.07
    coon
    -0.07
    mun
    -0.06
     большин
    -0.06
     ammon
    -0.06
     приня
    -0.06
    bose
    -0.06
    "sync
    -0.06
    POSITIVE LOGITS
     Havana
    0.06
    Char
    0.06
     druhý
    0.06
     plainly
    0.06
     Claims
    0.06
     carried
    0.06
    _argv
    0.06
    Titulo
    0.06
    ？
    0.06
     zag
    0.06
    Act Density 0.000%

    No Known Activations