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

    Neuronpedia

    INDEX
    Explanations

    listing steps and approximate values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᚐ
    0.33
     cùng
    0.33
    えた
    0.32
    ของการ
    0.32
     phẩm
    0.32
    ",&
    0.31
    ymo
    0.30
     ligeramente
    0.30
    ნდა
    0.30
     mencionado
    0.30
    POSITIVE LOGITS
     surrounding
    0.46
     surround
    0.46
     circulating
    0.42
     throughout
    0.42
     Throughout
    0.40
     circling
    0.39
     floating
    0.38
     everywhere
    0.36
     within
    0.35
     revolving
    0.35
    Act Density 5.603%

    No Known Activations