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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kişisel
    -0.06
    .score
    -0.06
     coincide
    -0.06
     neces
    -0.06
     полов
    -0.06
     brit
    -0.06
    anical
    -0.06
    tour
    -0.06
    eed
    -0.06
    arrera
    -0.06
    POSITIVE LOGITS
    同学
    0.07
    TG
    0.07
    ']/
    0.06
    /write
    0.06
    .ReadInt
    0.06
     '-';↵
    0.06
     Networking
    0.06
    、
    0.06
    正确
    0.06
    (stdout
    0.06
    Act Density 0.001%

    No Known Activations