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

    Neuronpedia

    INDEX
    Explanations

    exam questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coroutine
    -0.07
     등의
    -0.07
    ῶ
    -0.07
    ปกครอง
    -0.07
     český
    -0.07
     facade
    -0.07
     CheckBox
    -0.07
     matchup
    -0.06
     περί
    -0.06
     것으로
    -0.06
    POSITIVE LOGITS
     kt
    0.06
    Invite
    0.06
     Jwt
    0.06
    .Extension
    0.06
     मद
    0.06
    !!
    0.06
     millet
    0.06
    idot
    0.06
    _plate
    0.06
     "↵↵
    0.06
    Act Density 0.012%

    No Known Activations