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

    Neuronpedia

    INDEX
    Explanations

    names followed by words

    np_acts-logits-general · gemini-2.5-flash-lite

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.80
    as
    0.64
    l
    0.52
    y
    0.51
    s
    0.49
    tt
    0.49
    ta
    0.46
    ت
    0.46
    ai
    0.46
    tint
    0.46
    POSITIVE LOGITS
    يل
    0.51
    یر
    0.43
    によると
    0.41
    ד
    0.40
    ции
    0.40
     hướng
    0.39
    ე
    0.39
    B
    0.39
     beş
    0.39
     şöyle
    0.38
    Act Density 13.489%

    No Known Activations