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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    dz
    0.54
    a
    0.52
    sst
    0.49
    dv
    0.49
    dg
    0.49
    dl
    0.48
    "/
    0.48
    :
    0.48
    .,"
    0.46
    d
    0.46
    POSITIVE LOGITS
    ழை
    0.51
    াবেক
    0.49
    ḵ
    0.48
     ಪ್ರ
    0.46
    ్ర
    0.46
    피
    0.45
     ಉತ್ಪನ್ನ
    0.45
    जी
    0.44
    ור
    0.44
     물질
    0.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.