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

    Neuronpedia

    INDEX
    Explanations

    formal start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     व्यापारी
    0.38
    𝔯
    0.37
    予定
    0.35
    ियमित
    0.35
    勝ち
    0.34
    モデル
    0.33
     সমাজে
    0.33
    াণী
    0.33
     वापरा
    0.32
    cheduling
    0.32
    POSITIVE LOGITS
     initial
    1.13
     inicial
    1.06
     iniziale
    1.05
     Initial
    1.00
    initial
    0.98
     initiale
    0.96
    Initial
    0.93
     start
    0.88
     introductory
    0.88
     inital
    0.87
    Act Density 0.531%

    No Known Activations