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

    Neuronpedia

    INDEX
    Explanations

    explaining options and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    z
    1.27
    er
    1.05
    et
    1.04
    s
    1.02
    ים
    0.98
    a
    0.97
    '
    0.91
    g
    0.89
    ين
    0.88
    o
    0.83
    POSITIVE LOGITS
    จะ
    0.97
    เป็น
    0.94
     in
    0.92
    戦争
    0.81
    在
    0.79
    ری
    0.75
     all
    0.71
     அரசியல்
    0.70
    䛛
    0.70
     selesai
    0.69
    Act Density 0.468%

    No Known Activations