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

    Neuronpedia

    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ιά
    -0.07
    建設
    -0.06
    田
    -0.06
     lambda
    -0.06
     rude
    -0.06
    enek
    -0.06
     intentional
    -0.06
    ระบบ
    -0.06
     mắt
    -0.06
     kitt
    -0.06
    POSITIVE LOGITS
     Libya
    0.07
    گو
    0.07
    :hidden
    0.06
    кін
    0.06
    .Db
    0.06
    }}
    0.06
    <div
    0.06
     Xxx
    0.06
    по
    0.06
     →
    0.06
    Act Density 0.068%

    No Known Activations