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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yasak
    -0.07
     škola
    -0.07
    ソン
    -0.07
     DISCLAIM
    -0.07
    效
    -0.06
     solo
    -0.06
     Dam
    -0.06
     pb
    -0.06
    _game
    -0.06
    ्वत
    -0.06
    POSITIVE LOGITS
     حول
    0.06
     ثلاث
    0.06
     Duration
    0.06
     전에
    0.06
    े,
    0.06
    ++++++++
    0.06
    ]↵
    0.06
     leverage
    0.06
    Anywhere
    0.05
     wrestler
    0.05
    Act Density 0.049%

    No Known Activations