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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ģ«
    -0.67
    adj
    -0.62
     reelection
    -0.62
    riger
    -0.59
     247
    -0.58
     Contra
    -0.58
     Mixed
    -0.57
    bably
    -0.57
    Ĥª
    -0.56
     Aval
    -0.56
    POSITIVE LOGITS
    netflix
    0.79
     "$:/
    0.76
    icians
    0.74
    ypes
    0.71
    uminati
    0.69
    ocl
    0.67
    omal
    0.65
    âĸĦ
    0.64
    loads
    0.63
    heim
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.