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

    Neuronpedia

    INDEX
    Explanations

    means I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    them
    0.25
     Using
    0.23
     According
    0.22
    それを
    0.22
     podendo
    0.22
    これを
    0.21
     এটাকে
    0.21
    nYou
    0.21
     منه
    0.21
     ওকে
    0.21
    POSITIVE LOGITS
     there
    0.30
     neither
    0.23
     bureaucrats
    0.22
     ihe
    0.22
     ignoreString
    0.22
     assertFalse
    0.21
    noof
    0.21
     sabbam
    0.21
    there
    0.20
     attempts
    0.20
    Act Density 0.052%

    No Known Activations