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

    Neuronpedia

    INDEX
    Explanations

    communication media and messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ใน
    0.52
     in
    0.40
    .
    0.40
    ление
    0.40
    ໃນ
    0.39
     של
    0.38
     σε
    0.38
    ا
    0.38
    在
    0.37
    ography
    0.37
    POSITIVE LOGITS
    n
    0.66
    re
    0.57
    is
    0.53
    メッセージ
    0.53
    ли
    0.50
    message
    0.48
     for
    0.46
    m
    0.46
    d
    0.46
    c
    0.45
    Act Density 0.912%

    No Known Activations