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

    Neuronpedia

    INDEX
    Explanations

    please

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meeste
    -0.08
    .eye
    -0.08
    ája
    -0.08
     tub
    -0.08
     vemos
    -0.07
     goofy
    -0.07
     faithful
    -0.07
    levance
    -0.07
     joht
    -0.07
    ábamos
    -0.07
    POSITIVE LOGITS
     kindly
    0.12
     urgently
    0.11
     promptly
    0.11
     заранее
    0.09
     preferably
    0.09
     downloadable
    0.08
     ارسال
    0.08
     asap
    0.08
     пожалуйста
    0.08
     فر
    0.08
    Act Density 0.024%

    No Known Activations