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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     receives
    -0.07
     requires
    -0.06
     Kata
    -0.06
     이미
    -0.06
    <System
    -0.06
     ベ
    -0.06
    /dev
    -0.06
    Fs
    -0.06
     kat
    -0.06
    자인
    -0.06
    POSITIVE LOGITS
    론
    0.06
    ileges
    0.06
    ])),
    0.06
     '');↵↵
    0.06
    _context
    0.06
          ↵
    0.05
    幅
    0.05
    огра
    0.05
    ого
    0.05
    otech
    0.05
    Act Density 0.754%

    No Known Activations