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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     जाने
    -0.08
     ikut
    -0.07
     बिक
    -0.07
     naik
    -0.07
     bry
    -0.07
     Thread
    -0.07
     Schiff
    -0.07
     autem
    -0.07
     bằng
    -0.07
     clipped
    -0.07
    POSITIVE LOGITS
     જીવન
    0.09
     વચ્ચે
    0.08
    animate
    0.08
     પરિણામ
    0.08
     اختلاف
    0.08
     overcame
    0.08
    ીડ
    0.07
    Outcome
    0.07
     expediente
    0.07
     aspir
    0.07
    Act Density 0.043%

    No Known Activations