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

    Neuronpedia

    INDEX
    Explanations

    ortion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SITE
    -0.06
     classNames
    -0.06
    aseline
    -0.06
     жит
    -0.06
     souvis
    -0.06
     plaza
    -0.06
    +:
    -0.06
    ~~~~
    -0.06
    Numer
    -0.06
     kuru
    -0.06
    POSITIVE LOGITS
     abortion
    0.14
     abortions
    0.08
    moth
    0.06
    ]init
    0.06
    dom
    0.06
    ball
    0.06
    fort
    0.06
     shin
    0.06
     infr
    0.06
    uctive
    0.06
    Act Density 0.002%

    No Known Activations