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

    Neuronpedia

    INDEX
    Explanations

    Chinese reflections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RETURNS
    -0.08
     cartel
    -0.08
     bébé
    -0.08
     Engine
    -0.08
     trill
    -0.07
     Sponsored
    -0.07
     Padding
    -0.07
     engine
    -0.07
     cuotas
    -0.07
     ROUT
    -0.07
    POSITIVE LOGITS
    学习
    0.14
    心得
    0.13
    learning
    0.12
     gratitude
    0.12
     learning
    0.12
    个人
    0.12
    Personal
    0.12
     persönliche
    0.12
     personal
    0.12
     공부
    0.11
    Act Density 0.061%

    No Known Activations