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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     לבית
    -0.07
    inc
    -0.07
    ما
    -0.07
     did
    -0.07
    Confirm
    -0.06
    itung
    -0.06
    ო
    -0.06
     thực
    -0.06
     Wie
    -0.06
     Stanley
    -0.06
    POSITIVE LOGITS
    ustralia
    0.07
    不停的
    0.07
    cedure
    0.07
     locks
    0.07
     Tick
    0.07
    宝贝
    0.07
    DATES
    0.06
    PRE
    0.06
    pha
    0.06
    صاح
    0.06
    Act Density 0.011%

    No Known Activations