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

    Neuronpedia

    INDEX
    Explanations

    Creates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    برا
    0.48
    number
    0.43
     Oriented
    0.43
    achron
    0.41
     inspiration
    0.41
    小説
    0.40
     Paul
    0.39
     at
    0.39
    個性
    0.39
     eighth
    0.39
    POSITIVE LOGITS
     slaw
    0.51
     sosyal
    0.45
     souhait
    0.43
     শোষণ
    0.43
     ເ
    0.42
    ))`
    0.42
     roti
    0.41
     ಆಹಾರ
    0.41
     handels
    0.41
     sozial
    0.41
    Act Density 0.000%

    No Known Activations