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

    Neuronpedia

    INDEX
    Explanations

    Calculating weight and time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    園
    -0.08
     nations
    -0.07
    inei
    -0.07
     situated
    -0.07
     hearts
    -0.07
     tight
    -0.07
     piste
    -0.07
    war
    -0.07
    !")↵↵
    -0.07
     Encour
    -0.07
    POSITIVE LOGITS
    是多少
    0.09
    ాల్లో
    0.09
    .substr
    0.08
    ాలో
    0.08
    ాలి
    0.08
    _override
    0.08
    ులో
    0.08
     Skyl
    0.07
     politik
    0.07
    ాలను
    0.07
    Act Density 0.099%

    No Known Activations