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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tep
    -0.07
     acting
    -0.07
     Accounting
    -0.07
     OU
    -0.07
    פחד
    -0.07
    齁
    -0.07
    聪明
    -0.06
     להתמוד
    -0.06
    /template
    -0.06
     porcelain
    -0.06
    POSITIVE LOGITS
    .sa
    0.07
    .Remove
    0.07
    dates
    0.07
    സ
    0.07
     satur
    0.07
    .poll
    0.07
    inder
    0.07
    引发了
    0.07
    dere
    0.06
     denne
    0.06
    Act Density 0.065%

    No Known Activations