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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touchdowns
    -0.08
     quar
    -0.08
     참
    -0.07
    uert
    -0.07
     faded
    -0.07
     opges
    -0.07
     예방
    -0.07
     sabon
    -0.07
     втор
    -0.07
     bestätigt
    -0.07
    POSITIVE LOGITS
    特别
    0.12
     Besonders
    0.12
     standout
    0.11
     particulièrement
    0.11
    尤其
    0.11
     besonders
    0.11
     특히
    0.11
     particularmente
    0.10
     destaque
    0.10
     particularly
    0.10
    Act Density 0.308%

    No Known Activations