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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     various
    -0.10
     çeşitli
    -0.09
    各种
    -0.09
    Various
    -0.09
     დიდი
    -0.08
     Various
    -0.08
     આવેલા
    -0.08
     }}
    -0.08
     संबंधित
    -0.08
     दिए
    -0.08
    POSITIVE LOGITS
     testament
    0.22
     mélange
    0.16
     reminder
    0.15
     blend
    0.15
     testimony
    0.14
     mezcla
    0.14
     mixture
    0.13
     manifestation
    0.13
     fusion
    0.12
     Mischung
    0.12
    Act Density 0.072%

    No Known Activations