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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pork
    -0.06
    ”的
    -0.06
    _vi
    -0.06
     toddlers
    -0.06
    Spirit
    -0.06
    >',
    -0.06
    艾
    -0.06
    .team
    -0.06
     Fallen
    -0.06
     minden
    -0.06
    POSITIVE LOGITS
    emme
    0.07
    tabla
    0.07
     Hiệp
    0.07
    ichte
    0.06
    iu
    0.06
     cellar
    0.06
    uchs
    0.06
    Selectable
    0.06
     망
    0.06
    URY
    0.06
    Act Density 0.000%

    No Known Activations