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

    Neuronpedia

    INDEX
    Explanations

    Unusual text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。(
    -0.06
     azi
    -0.06
    _longitude
    -0.06
     چین
    -0.06
    iện
    -0.06
     mie
    -0.06
     IS
    -0.06
    Ba
    -0.06
    挂
    -0.06
    etag
    -0.06
    POSITIVE LOGITS
    Absolutely
    0.07
     Root
    0.07
    ocused
    0.07
    instant
    0.07
    entieth
    0.07
     학생
    0.06
    CURRENT
    0.06
    ursday
    0.06
    -bordered
    0.06
     Corbyn
    0.06
    Act Density 0.007%

    No Known Activations