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

    Neuronpedia

    INDEX
    Explanations

    code following again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     khal
    0.32
    П
    0.31
    裕
    0.31
    Ф
    0.30
    Pemb
    0.30
     soprattutto
    0.30
     basso
    0.30
    rape
    0.29
    Д
    0.29
    ﻧ
    0.29
    POSITIVE LOGITS
     Again
    0.70
    again
    0.62
     again
    0.59
    同樣
    0.59
    Again
    0.58
     opět
    0.57
    同样
    0.54
     yine
    0.54
    역시
    0.53
     опять
    0.53
    Act Density 0.099%

    No Known Activations