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

    Neuronpedia

    INDEX
    Explanations

    diagrams and their types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पहर
    0.45
     cherry
    0.40
     scorched
    0.38
     Scarlet
    0.38
    feo
    0.36
     স্বাদ
    0.36
     patties
    0.35
    绩
    0.35
     mah
    0.35
     pitted
    0.35
    POSITIVE LOGITS
     diagram
    3.81
    Diagram
    3.61
     diagrams
    3.58
     Diagram
    3.55
    diagram
    3.53
     Diagrams
    3.31
     diagrama
    3.16
    图
    2.28
    図
    2.28
    圖
    2.03
    Act Density 0.056%

    No Known Activations