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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utterstock
    -0.07
    .Imaging
    -0.07
    这事
    -0.06
    蘖
    -0.06
    はこちら
    -0.06
    กำไร
    -0.06
    쓺
    -0.06
     windowHeight
    -0.06
     billig
    -0.06
    ])):↵
    -0.06
    POSITIVE LOGITS
     Estados
    0.07
    libc
    0.07
     чис
    0.07
    舥
    0.06
     Ideal
    0.06
     =================================
    0.06
    src
    0.06
    .scal
    0.06
     merry
    0.06
    _trigger
    0.06
    Act Density 0.079%

    No Known Activations