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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gain
    -0.07
     AZ
    -0.06
    Rob
    -0.06
     indu
    -0.06
    otic
    -0.06
    west
    -0.06
    suffix
    -0.06
    森
    -0.06
    urg
    -0.06
    odo
    -0.06
    POSITIVE LOGITS
    “你
    0.07
    licensed
    0.07
     Сам
    0.07
     rites
    0.07
     donner
    0.07
     <
    0.06
    .compareTo
    0.06
     П
    0.06
    зано
    0.06
     accred
    0.06
    Act Density 0.010%

    No Known Activations