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

    Neuronpedia

    INDEX
    Explanations

    Gymnastics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uilder
    -0.07
    拓展
    -0.07
    裴
    -0.07
     Phil
    -0.06
    /non
    -0.06
    ותר
    -0.06
     hinter
    -0.06
    -for
    -0.06
     antes
    -0.06
     aspect
    -0.06
    POSITIVE LOGITS
    лим
    0.07
     łazienk
    0.07
    יהוד
    0.07
     woke
    0.07
    //!
    0.07
     المتعل
    0.07
     דיגיט
    0.07
    ество
    0.07
    科研院
    0.06
     footwear
    0.06
    Act Density 0.008%

    No Known Activations