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

    Neuronpedia

    INDEX
    Explanations

    Judge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asserting
    -0.07
    rück
    -0.07
     Gross
    -0.06
    PASS
    -0.06
     Assess
    -0.06
    Pass
    -0.06
    _table
    -0.06
    Obviously
    -0.06
    情况
    -0.06
     Arch
    -0.06
    POSITIVE LOGITS
    \Exception
    0.08
    icides
    0.07
    ﹽ
    0.07
    _EM
    0.07
    .two
    0.07
    .commons
    0.07
    encryption
    0.07
    iała
    0.07
    _players
    0.07
    aeper
    0.06
    Act Density 0.004%

    No Known Activations