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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    outs
    0.45
    out
    0.44
     out
    0.41
    Out
    0.40
     Out
    0.39
     worms
    0.38
     eis
    0.38
     norm
    0.38
     ক্রিকেট
    0.38
    norm
    0.37
    POSITIVE LOGITS
    定律
    0.48
     actuar
    0.43
    Accepted
    0.41
    Concent
    0.41
     เก็
    0.40
    ACCEPTED
    0.40
    ALSE
    0.40
     جيد
    0.39
     concent
    0.39
     consumir
    0.39
    Act Density 0.002%

    No Known Activations