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

    Neuronpedia

    INDEX
    Explanations

    Integer powers and divisibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propri
    -0.09
     Anton
    -0.09
     workshop
    -0.08
     sik
    -0.08
     Teatro
    -0.08
     Workshop
    -0.08
     ansi
    -0.07
    'label
    -0.07
     questo
    -0.07
     året
    -0.07
    POSITIVE LOGITS
    acu
    0.08
    בן
    0.07
    Remember
    0.07
    -more
    0.07
     restrictions
    0.07
     Remember
    0.07
     respondió
    0.07
    kent
    0.07
    டுக்க
    0.07
     responde
    0.07
    Act Density 0.002%

    No Known Activations