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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sebasti
    -0.08
    igol
    -0.07
    n't
    -0.07
    :innen
    -0.07
     Gauge
    -0.07
     अह
    -0.07
     Gib
    -0.07
     Werte
    -0.07
     semelhante
    -0.07
     Perd
    -0.07
    POSITIVE LOGITS
     aprendizaje
    0.10
     lifestyles
    0.08
    олч
    0.08
     entretenimiento
    0.08
     pastime
    0.08
     tidur
    0.08
     eid
    0.08
    ريح
    0.08
     tett
    0.08
     slapen
    0.08
    Act Density 0.016%

    No Known Activations