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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     інозем
    -0.06
     뭐
    -0.06
    ЛО
    -0.06
    favorites
    -0.06
     news
    -0.05
     waited
    -0.05
     #:
    -0.05
    บรร
    -0.05
     poru
    -0.05
     वन
    -0.05
    POSITIVE LOGITS
    )+'
    0.07
     Tunis
    0.07
     управления
    0.07
     camb
    0.06
     Ultr
    0.06
    iguous
    0.06
     rockets
    0.06
     BCM
    0.06
    igan
    0.06
     sẻ
    0.06
    Act Density 0.035%

    No Known Activations