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

    Neuronpedia

    INDEX
    Explanations

    compassion and generosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    1.61
    ."
    1.53
    ".
    1.44
     سکے۔
    1.40
    ।
    1.35
    」。
    1.34
     گی۔
    1.33
     。
    1.32
     ہے۔
    1.32
    ].
    1.31
    POSITIVE LOGITS
    ₂,
    1.94
     {},
    1.90
    /,
    1.86
    \%,
    1.81
     %,
    1.77
     [],
    1.76
    ?,
    1.76
    °,
    1.75
    ’,
    1.75
    **,
    1.74
    Act Density 1.994%

    No Known Activations