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

    Neuronpedia

    INDEX
    Explanations

    regex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sem
    -0.07
    ใหม
    -0.07
     iterator
    -0.06
     هند
    -0.06
     Clearly
    -0.06
    )n
    -0.06
     detects
    -0.06
    'a
    -0.06
    )<=
    -0.06
    활동
    -0.06
    POSITIVE LOGITS
     истории
    0.07
    ław
    0.06
     ;
    0.06
    MG
    0.06
     nguyên
    0.06
    แนว
    0.06
     Alphabet
    0.06
     rf
    0.06
     feudal
    0.06
     Www
    0.06
    Act Density 0.021%

    No Known Activations