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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buffalo
    -0.07
    Atual
    -0.07
    敷
    -0.07
     lavor
    -0.07
     promotes
    -0.06
     asbestos
    -0.06
    習
    -0.06
    intersect
    -0.06
    屋
    -0.06
     Οκ
    -0.06
    POSITIVE LOGITS
    (media
    0.07
    则
    0.07
     Tier
    0.07
    361
    0.06
    _hi
    0.06
     embed
    0.06
    .Int
    0.06
    _MARKER
    0.06
     米
    0.06
    oa
    0.06
    Act Density 0.021%

    No Known Activations