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

    Neuronpedia

    INDEX
    Explanations

    header

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     треть
    -0.07
    oksen
    -0.07
    gili
    -0.06
     COST
    -0.06
    配合
    -0.06
     Dop
    -0.06
    rijk
    -0.06
    ies
    -0.06
     Soy
    -0.06
     heaters
    -0.06
    POSITIVE LOGITS
    NPC
    0.07
     cantidad
    0.06
    قى
    0.06
     verbal
    0.06
    iana
    0.06
    -term
    0.06
     QVector
    0.06
     recap
    0.06
     ben
    0.06
     scanf
    0.06
    Act Density 0.012%

    No Known Activations