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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    норийска
    0.40
    parsedBlock
    0.40
     amplio
    0.39
     stereotyp
    0.39
    ḕ
    0.39
     byli
    0.39
     complainants
    0.38
     litigants
    0.38
    infodisc
    0.38
     conciencia
    0.38
    POSITIVE LOGITS
    1
    0.63
    2
    0.61
    5
    0.61
    0
    0.60
    4
    0.60
    3
    0.53
    One
    0.53
    6
    0.52
    9
    0.51
    .
    0.50
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.