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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ities
    -0.07
     wrappers
    -0.06
     landmarks
    -0.06
    itation
    -0.06
     Kitchen
    -0.06
     II
    -0.06
    Out
    -0.06
     output
    -0.06
    _owner
    -0.06
     airborne
    -0.06
    POSITIVE LOGITS
    战争
    0.07
     elders
    0.07
     edin
    0.07
    .Locale
    0.07
    untlet
    0.07
    ��
    0.06
    bserv
    0.06
    .Visual
    0.06
    ไทย
    0.06
     arkadaş
    0.06
    Act Density 0.005%

    No Known Activations