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

    Neuronpedia

    INDEX
    Explanations

    translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .example
    -0.07
    PHONE
    -0.07
     ụdị
    -0.07
    Sun
    -0.07
    .global
    -0.07
     tomato
    -0.07
     ehem
    -0.07
     examples
    -0.07
    .examples
    -0.07
     appear
    -0.06
    POSITIVE LOGITS
     পর
    0.09
    /function
    0.08
    /context
    0.08
     morto
    0.08
     ग्राम
    0.08
     moro
    0.08
    及
    0.07
     لا
    0.07
    ্কার
    0.07
     পাশাপাশি
    0.07
    Act Density 0.035%

    No Known Activations