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

    Neuronpedia

    INDEX
    Explanations

    graphical representations and diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    citenamefont
    0.39
     notizia
    0.37
     stagione
    0.37
     ഉറ
    0.36
     leasing
    0.36
    crackers
    0.36
     seasonings
    0.36
     announcements
    0.35
     seasoning
    0.35
    ラクマ
    0.35
    POSITIVE LOGITS
     diagram
    2.08
     diagrams
    1.94
    Diagram
    1.89
    diagram
    1.82
     Diagram
    1.80
     diagrama
    1.69
     Diagrams
    1.65
     graphical
    1.62
    图
    1.52
     graphically
    1.43
    Act Density 0.068%

    No Known Activations