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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _outputs
    -0.07
    (System
    -0.07
    =\'
    -0.06
    _engine
    -0.06
    _devices
    -0.06
    identally
    -0.06
     analyzed
    -0.06
    _old
    -0.06
    (ID
    -0.06
    서
    -0.06
    POSITIVE LOGITS
    +
    0.09
     +
    0.09
    weather
    0.07
    +)
    0.07
     lep
    0.06
    lowest
    0.06
    impan
    0.06
     успеш
    0.06
    est
    0.06
    okane
    0.06
    Act Density 0.003%

    No Known Activations