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

    Neuronpedia

    INDEX
    Explanations

    List

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .assertAlmostEqual
    -0.07
     вла
    -0.07
    _INPUT
    -0.07
    uitka
    -0.06
    .updated
    -0.06
    edu
    -0.06
     деятельности
    -0.06
     Hải
    -0.06
    _il
    -0.06
    nob
    -0.06
    POSITIVE LOGITS
    _one
    0.06
     بهتر
    0.06
     believed
    0.06
    anden
    0.06
     darkness
    0.06
    (Application
    0.06
     Twist
    0.06
     HttpHeaders
    0.06
    -page
    0.06
     любой
    0.06
    Act Density 0.000%

    No Known Activations