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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.90
    çīĪ
    -0.83
     ANN
    -0.76
    ä¸Ĭ
    -0.72
    theless
    -0.71
    ãĥ´
    -0.70
    åĭ
    -0.70
     å¤
    -0.69
    housing
    -0.69
    burgh
    -0.69
    POSITIVE LOGITS
    ilater
    0.74
     authorised
    0.68
     actionGroup
    0.64
     Lizard
    0.61
     quarantine
    0.61
     Natural
    0.60
     favour
    0.59
     IPA
    0.59
     apart
    0.58
     regulators
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.