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

    Neuronpedia

    INDEX
    Explanations

    为

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utowired
    -0.08
     Strauss
    -0.07
     Barton
    -0.07
    _locs
    -0.07
     verwenden
    -0.07
    strncmp
    -0.07
     الاخ
    -0.07
     Electron
    -0.07
     материал
    -0.07
    (dev
    -0.06
    POSITIVE LOGITS
    对
    0.10
     对
    0.08
    ，对
    0.07
     colorful
    0.07
     armored
    0.06
    model
    0.06
     Amount
    0.06
     Wolf
    0.06
    村
    0.06
    fb
    0.06
    Act Density 0.006%

    No Known Activations