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

    Neuronpedia

    INDEX
    Explanations

    length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    On
    -3.42
    {
    -3.39
    After
    -3.27
    When
    -3.19
    Our
    -3.14
    While
    -3.11
    The
    -2.97
    During
    -2.94
    What
    -2.92
    There
    -2.91
    POSITIVE LOGITS
    驺
    2.61
    韪
    2.38
    ophageal
    2.38
    鞴
    2.31
    ſſi
    2.31
    釤
    2.31
    
    2.27
    踽
    2.25
    媪
    2.25
    銫
    2.23
    Act Density 0.001%

    No Known Activations