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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imon
    -0.07
    屋
    -0.07
    .median
    -0.07
     turist
    -0.07
     tran
    -0.06
    hive
    -0.06
    unic
    -0.06
    μμ
    -0.06
    緊
    -0.06
    ítulo
    -0.06
    POSITIVE LOGITS
     сп
    0.07
     veil
    0.06
     distinctions
    0.06
    .Floor
    0.06
    机会
    0.06
     Newport
    0.06
     optics
    0.06
     activities
    0.06
     firefight
    0.06
    .isSuccess
    0.06
    Act Density 0.010%

    No Known Activations