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

    Neuronpedia

    INDEX
    Explanations

    source, sources, of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    警察
    -0.08
     Yayın
    -0.07
    exam
    -0.07
    اهد
    -0.07
     natuur
    -0.06
    ागत
    -0.06
    BackColor
    -0.06
    redential
    -0.06
    اطر
    -0.06
     quer
    -0.06
    POSITIVE LOGITS
    carry
    0.07
     tuberculosis
    0.06
    ncpy
    0.06
     Siz
    0.05
     точ
    0.05
    TestMethod
    0.05
    _DEV
    0.05
     subs
    0.05
    _OF
    0.05
     punched
    0.05
    Act Density 0.005%

    No Known Activations