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

    Neuronpedia

    INDEX
    Explanations

    own memory (VRAM)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    צא
    0.50
    דע
    0.48
     Superintendent
    0.45
     Commissioner
    0.45
    חד
    0.43
     Association
    0.42
    zata
    0.41
     ASSOCIATION
    0.41
    Commissioner
    0.40
     Gala
    0.39
    POSITIVE LOGITS
    тт
    0.41
    сті
    0.38
     நிற்கும்
    0.38
     trai
    0.38
     lai
    0.38
     biển
    0.37
    抔
    0.37
    くい
    0.37
     shroud
    0.37
    وشی
    0.37
    Act Density 0.000%

    No Known Activations