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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patriarch
    -0.07
    _LEAVE
    -0.06
     captain
    -0.06
     mention
    -0.06
    Updates
    -0.06
    indicator
    -0.06
    -router
    -0.06
     loaded
    -0.06
     citiz
    -0.06
    Fill
    -0.06
    POSITIVE LOGITS
    [,
    0.07
    .ver
    0.06
    down
    0.06
    +/
    0.06
    ιας
    0.06
    کم
    0.06
     mushroom
    0.06
    420
    0.06
    ाल
    0.06
    İS
    0.06
    Act Density 0.008%

    No Known Activations