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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mich
    -0.07
     yuk
    -0.07
    인지
    -0.07
    hh
    -0.07
    ⎳
    -0.06
     Mich
    -0.06
     lush
    -0.06
    uch
    -0.06
    舒适
    -0.06
    有着
    -0.06
    POSITIVE LOGITS
     Saudis
    0.07
    _crypto
    0.07
     podemos
    0.07
    cribes
    0.07
    .resize
    0.07
     carrots
    0.06
     interpreted
    0.06
    Präs
    0.06
    auen
    0.06
     bowel
    0.06
    Act Density 0.032%

    No Known Activations