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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    zież
    0.38
    azał
    0.38
     reimag
    0.36
    ották
    0.36
    ampton
    0.36
    elevationMap
    0.36
    ără
    0.35
    utiérrez
    0.35
    aithe
    0.35
    arovski
    0.35
    POSITIVE LOGITS
    0
    0.60
    _
    0.57
    4
    0.55
    1
    0.54
    5
    0.54
    6
    0.51
    2
    0.49
    3
    0.48
    7
    0.48
    8
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.