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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mindful
    -0.09
    (tok
    -0.07
     diligent
    -0.07
     delin
    -0.07
     fascinated
    -0.07
    arant
    -0.07
     renting
    -0.07
    留下
    -0.07
     celo
    -0.07
     ప
    -0.07
    POSITIVE LOGITS
     incorrect
    0.13
     incorrectly
    0.12
    incorrect
    0.11
     Incorrect
    0.11
    Incorrect
    0.11
     wrong
    0.10
    wrong
    0.10
     wrongly
    0.10
     चुकी
    0.09
     errone
    0.09
    Act Density 0.086%

    No Known Activations