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

    Neuronpedia

    INDEX
    Explanations

    substrate descriptions and uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    1.36
     불구하고
    1.00
    𝗯
    1.00
    ر
    0.91
    ਮ
    0.88
    ナ
    0.87
    ர
    0.86
    ア
    0.84
    が存在
    0.84
    aría
    0.82
    POSITIVE LOGITS
     MPs
    1.17
     (
    1.15
     s
    0.99
    _
    0.99
     attendants
    0.94
     CNC
    0.94
     stare
    0.93
     eller
    0.92
     for
    0.92
    <0x0D>
    0.91
    Act Density 0.001%

    No Known Activations