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

    Neuronpedia

    INDEX
    Explanations

    answer is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    埬
    0.37
    >',
    0.36
    㘿
    0.36
    ">//
    0.36
    WING
    0.36
    ,*/}*.
    0.36
    ಕಿ
    0.35
     linemen
    0.35
    ौली
    0.34
    '];?>
    0.34
    POSITIVE LOGITS
    ՝
    0.35
    ><
    0.33
    ⠉
    0.32
     \,
    0.32
     mantenimiento
    0.32
    ിക്കുന്ന
    0.32
    ༅
    0.32
     fortemente
    0.31
    ̥
    0.30
     ۔۔
    0.30
    Act Density 0.076%

    No Known Activations