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

    Neuronpedia

    INDEX
    Explanations

    reflections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дост
    -0.08
     unofficial
    -0.08
     oversight
    -0.08
     Senators
    -0.07
     outreach
    -0.07
     diesel
    -0.07
     overlooked
    -0.07
     oversees
    -0.07
    副
    -0.07
     അധിക
    -0.07
    POSITIVE LOGITS
     ครั้ง
    0.09
    reflection
    0.09
     flam
    0.08
    bra
    0.08
     ymp
    0.08
     פעם
    0.08
    ళ్ల
    0.08
    laser
    0.08
     sociedades
    0.08
    ళ్ళ
    0.08
    Act Density 0.012%

    No Known Activations