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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     或
    0.62
     அல்லது
    0.61
     или
    0.57
     أو
    0.54
     یا
    0.54
     หรือ
    0.53
     Или
    0.53
     hMut
    0.53
     or
    0.51
     અથવા
    0.50
    POSITIVE LOGITS
    _
    0.79
    -_
    0.77
    _.
    0.74
    ._
    0.65
    ws
    0.65
    '_
    0.64
    1
    0.63
    _[
    0.61
    2
    0.61
    _=
    0.59
    Act Density 0.044%

    No Known Activations