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

    Neuronpedia

    INDEX
    Explanations

    during file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arr
    0.50
     see
    0.47
    auf
    0.47
    ording
    0.46
     If
    0.46
    man
    0.45
    link
    0.45
    <>(
    0.45
    If
    0.45
     That
    0.44
    POSITIVE LOGITS
     其
    0.49
    ດີ
    0.48
    ミリー
    0.47
    鏽
    0.47
    ೋಗ
    0.47
     INDUSTR
    0.47
    CHEMY
    0.46
    其
    0.46
    ເຄື່ອງ
    0.46
    리를
    0.46
    Act Density 0.001%

    No Known Activations