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

    Neuronpedia

    INDEX
    Explanations

    URLs with numbers and hyphens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கை
    0.29
     accepter
    0.28
    மாகக்
    0.28
     "${
    0.27
    Selection
    0.27
    Pixel
    0.27
     են
    0.27
    dataIn
    0.26
    菟
    0.26
     log
    0.26
    POSITIVE LOGITS
    /?
    0.34
    ;_
    0.34
    ?-
    0.33
     anyways
    0.32
     расскажем
    0.32
    /#
    0.32
     FAQs
    0.32
    zechoslovakia
    0.31
    faq
    0.31
     veja
    0.31
    Act Density 0.017%

    No Known Activations