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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Disagree
    0.39
    idu
    0.39
     Nerd
    0.38
     খাবার
    0.38
    Flipper
    0.38
     ব্যক্তিত্ব
    0.37
    Len
    0.37
    গান
    0.37
    文章
    0.37
     น้อย
    0.37
    POSITIVE LOGITS
     prelude
    0.58
     Prelude
    0.54
     prequel
    0.52
     wrath
    0.51
     Reload
    0.50
     rebirth
    0.50
     Homecoming
    0.48
    新た
    0.45
     sequel
    0.44
     Towards
    0.44
    Act Density 0.008%

    No Known Activations