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

    Neuronpedia

    INDEX
    Explanations

    Regular expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bulls
    -0.08
     Espagne
    -0.08
     hala
    -0.07
    arlar
    -0.07
     plafond
    -0.07
     électriques
    -0.07
     listrik
    -0.07
     assass
    -0.07
     manuals
    -0.07
     bulls
    -0.07
    POSITIVE LOGITS
    -many
    0.10
     repetitions
    0.09
     რაოდენ
    0.09
     permiss
    0.09
    -repeat
    0.09
    |required
    0.08
    .repeat
    0.08
     ერთად
    0.08
     ಕೋಟ
    0.08
    จำนวน
    0.08
    Act Density 0.003%

    No Known Activations