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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    =-=-=-=-
    -0.82
    throp
    -0.80
    Downloadha
    -0.79
    uries
    -0.75
    urs
    -0.71
    esses
    -0.70
     Voices
    -0.70
    zbollah
    -0.69
     Consumers
    -0.68
    racuse
    -0.67
    POSITIVE LOGITS
     light
    1.39
    gate
    0.83
    Assembly
    0.72
    Light
    0.68
    ^{
    0.67
     spiral
    0.66
     Light
    0.65
    minster
    0.65
    Gate
    0.64
     dwarf
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.