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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    거
    0.73
     sheep
    0.72
     deflation
    0.64
     prosecutions
    0.64
     бъдат
    0.64
     paraly
    0.64
     xung
    0.61
     compounds
    0.61
     страхо
    0.61
     vapour
    0.60
    POSITIVE LOGITS
    bereitung
    0.99
     inicios
    0.93
    loxy
    0.89
    durch
    0.89
    مون
    0.89
    d
    0.86
    れて
    0.84
    rdoba
    0.84
     lujo
    0.83
    rimos
    0.83
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.