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

    Neuronpedia

    INDEX
    Explanations

    constraints, limitations, or negative aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     നിങ്ങൾ
    0.75
    ల
    0.74
     நீங்கள்
    0.72
     మీరు
    0.67
    ка
    0.66
     ভাগ
    0.64
    പോ
    0.64
    Puzzle
    0.64
    హ
    0.64
    রণ
    0.64
    POSITIVE LOGITS
    !,
    2.01
    ?,
    1.81
    (),
    1.77
    ,)
    1.55
    ₂,
    1.51
    °,
    1.47
     [],
    1.46
    ’,
    1.45
    ™,
    1.44
    ),
    1.43
    Act Density 0.203%

    No Known Activations