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

    Neuronpedia

    INDEX
    Explanations

    edX, Udemy, Coursera

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izados
    0.40
     deletions
    0.38
    ؤں
    0.37
     sost
    0.36
     recite
    0.36
    ணர்வு
    0.36
     sediment
    0.35
     Udd
    0.35
     Erosion
    0.35
     possession
    0.34
    POSITIVE LOGITS
    Shel
    0.44
    فيف
    0.41
    acuation
    0.41
    uski
    0.40
    umac
    0.39
    Semif
    0.39
    羞
    0.39
    ◉
    0.38
     Shel
    0.38
    URO
    0.37
    Act Density 0.001%

    No Known Activations