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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ????
    0.44
     ???
    0.42
    ????????
    0.39
     etc
    0.38
     परवानगी
    0.38
     \
    0.37
    ?????
    0.37
     Very
    0.36
     방정
    0.36
    ~\
    0.36
    POSITIVE LOGITS
     مسلح
    0.41
    armed
    0.37
    logistic
    0.36
    abbas
    0.35
    conj
    0.34
    advertise
    0.34
    スケ
    0.33
    (/^
    0.33
    onal
    0.33
    豹
    0.33
    Act Density 0.000%

    No Known Activations