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

    Neuronpedia

    INDEX
    Explanations

    common grammatical words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /tutorial
    -0.07
     achter
    -0.07
    قية
    -0.07
    身体
    -0.06
    _hr
    -0.06
     Zag
    -0.06
     Giz
    -0.06
     "*"
    -0.06
    (doc
    -0.06
    motor
    -0.06
    POSITIVE LOGITS
    těl
    0.07
     executes
    0.06
     performs
    0.06
    \Abstract
    0.06
     CACHE
    0.06
    ║
    0.06
     类
    0.06
    vailability
    0.06
     our
    0.06
    lost
    0.06
    Act Density 0.496%

    No Known Activations