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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "While
    -0.07
    孔
    -0.07
     увели
    -0.07
    "This
    -0.07
    階
    -0.06
    ћ
    -0.06
     欧
    -0.06
    멘
    -0.06
     anonymous
    -0.06
     resale
    -0.06
    POSITIVE LOGITS
    InvalidArgumentException
    0.07
    _inactive
    0.07
    managed
    0.07
    antanamo
    0.07
    ($_
    0.06
    .imageView
    0.06
    .ge
    0.06
     FontWeight
    0.06
    ::$
    0.06
    =findViewById
    0.06
    Act Density 0.498%

    No Known Activations