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

    Neuronpedia

    INDEX
    Explanations

    text structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TargetPath
    0.61
    goog
    0.58
    콩
    0.57
     قض
    0.56
     ставка
    0.54
    摘要
    0.54
     midline
    0.54
     ставки
    0.53
     subgoal
    0.53
    一番
    0.52
    POSITIVE LOGITS
     shooter
    0.55
     beeindruck
    0.54
    కంగా
    0.52
     Mora
    0.52
     veins
    0.51
    otin
    0.50
    amus
    0.50
    shooter
    0.50
    नेटिक
    0.50
     Cane
    0.50
    Act Density 0.000%

    No Known Activations