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

    Neuronpedia

    INDEX
    Explanations

    propensity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    이어
    -0.07
     stare
    -0.07
     Вас
    -0.07
    حي
    -0.07
    .Run
    -0.07
     elé
    -0.07
    .bottom
    -0.06
    卢
    -0.06
    };↵
    -0.06
     дія
    -0.06
    POSITIVE LOGITS
     propensity
    0.16
     penchant
    0.11
     affinity
    0.08
     Companion
    0.07
     shader
    0.06
     Authors
    0.06
    ccb
    0.06
     knack
    0.06
     ธ
    0.06
    SK
    0.06
    Act Density 0.001%

    No Known Activations