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

    Neuronpedia

    INDEX
    Explanations

    etiquette and manners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    하자
    -0.07
     �
    -0.07
    ----↵
    -0.07
    ----↵↵
    -0.06
     TECHNO
    -0.06
    opis
    -0.06
     formatting
    -0.06
    ':↵↵
    -0.06
     contours
    -0.06
     Morton
    -0.06
    POSITIVE LOGITS
    CLUD
    0.07
    を開
    0.06
    focused
    0.06
    hood
    0.06
    чних
    0.06
    Pass
    0.06
    ursday
    0.06
     봉
    0.06
     flexDirection
    0.06
    (header
    0.06
    Act Density 0.136%

    No Known Activations