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
    itev
    -0.08
     rā
    -0.08
     पहिले
    -0.08
     निधन
    -0.08
     mbụ
    -0.07
     साह
    -0.07
    צה
    -0.07
     cohesive
    -0.07
    imwe
    -0.07
     pins
    -0.07
    POSITIVE LOGITS
     Umgang
    0.15
    扱
    0.13
     manipulating
    0.10
     dealings
    0.10
     manipulation
    0.10
    beitung
    0.09
     التعامل
    0.09
     Manip
    0.09
     обращаться
    0.09
     Verarbeitung
    0.09
    Act Density 0.032%

    No Known Activations