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

    Neuronpedia

    INDEX
    Explanations

    research proposal paper advisor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    в
    2.61
    plemented
    2.05
    ,\,
    2.00
    Aunque
    1.98
    ון
    1.96
     быть
    1.94
     nadi
    1.91
    siehe
    1.91
    🄰
    1.87
    rm
    1.87
    POSITIVE LOGITS
    ের
    2.33
    manship
    2.20
    aient
    2.17
    s
    2.12
    িং
    2.11
    sight
    1.99
    song
    1.99
    ки
    1.97
    ك
    1.93
    ণের
    1.92
    Act Density 0.113%

    No Known Activations