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

    Neuronpedia

    INDEX
    Explanations

    empath

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (strlen
    -0.08
     performan
    -0.07
    ountains
    -0.07
     якості
    -0.07
    UST
    -0.06
    crast
    -0.06
    RAINT
    -0.06
    legate
    -0.06
    .sax
    -0.06
    ublished
    -0.06
    POSITIVE LOGITS
    沒
    0.07
    .By
    0.06
     Respond
    0.06
     doesn
    0.06
     Patel
    0.06
    -lo
    0.06
    /*↵
    0.06
    Small
    0.06
    Phone
    0.06
    Peace
    0.06
    Act Density 0.000%

    No Known Activations