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

    Neuronpedia

    INDEX
    Explanations

    registered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Volumes
    -0.07
    034
    -0.07
     admir
    -0.07
     BITTE
    -0.07
    恩
    -0.07
     뛰
    -0.06
    _LCD
    -0.06
    _bed
    -0.06
    ird
    -0.06
    dden
    -0.06
    POSITIVE LOGITS
    serial
    0.07
     worthless
    0.07
    modern
    0.06
    sources
    0.06
    metro
    0.06
     cele
    0.06
    xis
    0.06
    chrono
    0.06
     specifies
    0.06
     preferring
    0.06
    Act Density 0.002%

    No Known Activations