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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wé
    -0.09
     рассказ
    -0.08
     wholesome
    -0.08
    visional
    -0.08
     dangers
    -0.08
     Helpful
    -0.07
    iski
    -0.07
    عه
    -0.07
     взгляд
    -0.07
     creepy
    -0.07
    POSITIVE LOGITS
     Ihres
    0.11
     your
    0.11
     Ihrer
    0.11
     ailleurs
    0.09
     vostre
    0.09
     вашей
    0.09
    your
    0.09
     دارید
    0.09
    您的
    0.09
     لديك
    0.09
    Act Density 0.042%

    No Known Activations