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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    NE
    0.45
     weight
    0.45
     dose
    0.44
    0.44
    нути
    0.44
    PL
    0.43
    سي
    0.42
     cure
    0.42
     trecut
    0.42
    нула
    0.42
    POSITIVE LOGITS
     assumptive
    0.48
    Ყ
    0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
     GTEST
    0.46
    xes
    0.46
    მასრულ
    0.46
    dns
    0.45
     изменения
    0.45
     APIDC
    0.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.