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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Tot
    0.45
    <h5>
    0.41
    comments
    0.41
    poll
    0.40
    revise
    0.40
    ut
    0.39
    categories
    0.39
    Series
    0.39
    category
    0.38
    boa
    0.38
    POSITIVE LOGITS
    ГА
    0.45
    ুনা
    0.42
     vucc
    0.39
     obchod
    0.39
    䚯
    0.39
     punishable
    0.38
     puestos
    0.38
    га
    0.38
     protegido
    0.38
    VJ
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.