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
    .u
    -0.07
     Achievement
    -0.07
    stamp
    -0.07
    pants
    -0.07
    '_
    -0.06
    pire
    -0.06
    results
    -0.06
     mName
    -0.06
    Pow
    -0.06
    _equals
    -0.06
    POSITIVE LOGITS
    .destroyAllWindows
    0.07
    ,key
    0.07
    (samples
    0.07
    ght
    0.06
     üz
    0.06
    ,None
    0.06
     Оп
    0.06
     Bernardino
    0.06
    *******************************************************************************/↵
    0.06
    áty
    0.06
    Act Density 0.012%

    No Known Activations