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

    Neuronpedia

    INDEX
    Explanations

    multilingual structural indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     psal
    0.51
     oven
    0.41
     contraction
    0.41
     bath
    0.40
     indulgence
    0.39
     undead
    0.39
     mulch
    0.38
     socialists
    0.38
     hens
    0.38
     atrophy
    0.38
    POSITIVE LOGITS
     справо
    0.43
     подробно
    0.42
    $\
    0.41
     Objectives
    0.41
     Presented
    0.41
     Почему
    0.40
     பெறு
    0.40
     Chapter
    0.39
     Mitchell
    0.39
     সরল
    0.39
    Act Density 0.005%

    No Known Activations