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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    And
    0.52
    ت
    0.48
    اب
    0.47
     Europ
    0.47
    oth
    0.46
    hem
    0.45
    neat
    0.45
    pc
    0.44
    Am
    0.43
    ropolitan
    0.43
    POSITIVE LOGITS
     बेसब
    0.56
    ερ
    0.54
    ﺄ
    0.53
     ACTIONS
    0.52
     lysine
    0.52
     yakin
    0.52
     रझा
    0.51
     subunits
    0.50
     প্রার্থনা
    0.50
     PAR
    0.49
    Act Density 0.002%

    No Known Activations