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

    Neuronpedia

    INDEX
    Explanations

    yellow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    astaan
    -0.09
    -0.09
     Pellet
    -0.08
     siège
    -0.08
    orados
    -0.08
     dearly
    -0.07
     paroles
    -0.07
     положения
    -0.07
     الحجم
    -0.07
     René
    -0.07
    POSITIVE LOGITS
     undert
    0.08
    Feeling
    0.08
     grape
    0.08
     gloomy
    0.08
     upset
    0.08
     ఉంద
    0.08
     ఉంటుంది
    0.07
     warmth
    0.07
    Reading
    0.07
     frio
    0.07
    Act Density 0.007%
    No Known Activations