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

    Neuronpedia

    INDEX
    Explanations

    best version of themselves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rst
    -0.07
    inations
    -0.07
    给我们
    -0.07
    给你
    -0.07
     wissen
    -0.07
     neph
    -0.07
     Pension
    -0.07
    贻
    -0.07
     const
    -0.07
     Didn
    -0.07
    POSITIVE LOGITS
    ;z
    0.08
    etc
    0.07
    โบรา
    0.07
    Ҥ
    0.07
    ༼
    0.07
     frags
    0.07
     parity
    0.07
    (#)
    0.07
    Feels
    0.06
    (CH
    0.06
    Act Density 0.020%

    No Known Activations