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

    Neuronpedia

    INDEX
    Explanations

    job titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OM
    -0.07
    .Cache
    -0.07
    GINE
    -0.06
    -frame
    -0.06
    مین
    -0.06
     hommes
    -0.06
    ريس
    -0.06
    _ret
    -0.06
     欧
    -0.06
    -direct
    -0.06
    POSITIVE LOGITS
    ichick
    0.07
     Mö
    0.07
    하고
    0.06
     Describe
    0.06
     shortfall
    0.06
     PO
    0.06
    nul
    0.06
    -special
    0.06
    ､_
    0.06
     Sicher
    0.06
    Act Density 0.027%

    No Known Activations