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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    erti
    -0.28
    centration
    -0.26
    iken
    -0.25
     Kumar
    -0.24
    rire
    -0.24
    Someone
    -0.23
     Shark
    -0.23
    ITION
    -0.23
    mars
    -0.23
    Washington
    -0.23
    POSITIVE LOGITS
     shred
    0.29
     expelled
    0.26
    容
    0.26
    ä¸įæŃ»
    0.25
     escap
    0.25
    AndView
    0.24
    ÕŃ
    0.24
    çݯçIJĥ
    0.24
    ¢åįķ
    0.24
    à¹Īà¸Ńย
    0.24
    Act Density 0.074%

    No Known Activations

    This feature has no known activations.