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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Haw
    -0.07
    _RAW
    -0.06
    !";
↵
    -0.06
    brero
    -0.06
     Rugby
    -0.06
    emphasis
    -0.06
     öğret
    -0.06
     आम
    -0.06
     rotational
    -0.06
    Lets
    -0.06
    POSITIVE LOGITS
     INTO
    0.08
    jamin
    0.07
     奥
    0.07
     Into
    0.07
    -rays
    0.07
     tersebut
    0.06
     thigh
    0.06
    (::
    0.06
    ะแนน
    0.06
     Neck
    0.06
    Act Density 0.006%

    No Known Activations