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

    Neuronpedia

    INDEX
    Explanations

    coding and algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     현실
    -0.09
     nhà
    -0.08
    Luxury
    -0.08
    adox
    -0.08
     atrak
    -0.08
    .Range
    -0.08
     مطرح
    -0.08
     বক্ত
    -0.08
     Heaven
    -0.08
     확대
    -0.07
    POSITIVE LOGITS
     manually
    0.12
     computed
    0.10
     debugging
    0.09
     calculation
    0.09
     values
    0.09
     algorithm
    0.09
     passo
    0.09
     compute
    0.09
     вычис
    0.09
     calculate
    0.08
    Act Density 0.026%

    No Known Activations