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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pět
    -0.07
    銀
    -0.07
    별
    -0.07
    ládání
    -0.07
    attro
    -0.07
    غل
    -0.07
    čer
    -0.07
     sizable
    -0.07
    บอล
    -0.06
     dei
    -0.06
    POSITIVE LOGITS
    )p
    0.06
    /twitter
    0.06
     Apprent
    0.06
     enclosed
    0.06
    dock
    0.06
    �
    0.06
    _dropout
    0.06
     runes
    0.06
    ucz
    0.06
     unittest
    0.06
    Act Density 0.036%

    No Known Activations