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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arap
    -0.07
    빈
    -0.07
    Concept
    -0.06
     averaging
    -0.06
    $p
    -0.06
    elog
    -0.06
     протягом
    -0.06
    _FINAL
    -0.06
     aiming
    -0.06
    ("").
    -0.06
    POSITIVE LOGITS
     proceso
    0.08
     ruthless
    0.07
     Bedroom
    0.07
    宙
    0.07
     bä
    0.07
    zimmer
    0.07
    <Guid
    0.06
    pectral
    0.06
     الشي
    0.06
     внеш
    0.06
    Act Density 0.004%

    No Known Activations