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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     듯
    -0.07
    ここ
    -0.07
    �
    -0.07
    еи
    -0.06
     ErrorResponse
    -0.06
    ansk
    -0.06
     elapsedTime
    -0.06
    Protect
    -0.06
    ultipart
    -0.06
     skl
    -0.06
    POSITIVE LOGITS
     підт
    0.07
    體
    0.06
     handle
    0.06
    689
    0.06
     reps
    0.06
    жа
    0.06
    ((_
    0.06
    −
    0.06
    _associ
    0.06
    Narrated
    0.06
    Act Density 0.032%

    No Known Activations