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

    Neuronpedia

    INDEX
    Explanations

    if followed by (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \"
    0.76
    +,
    0.75
    $-$
    0.72
    ’.
    0.71
     आशीष
    0.70
    ுங்கள்
    0.70
     $-
    0.70
    ​,
    0.69
    ”;
    0.69
    \]
    0.69
    POSITIVE LOGITS
     (!
    1.67
    (!
    1.62
     ((
    1.62
    ((
    1.54
     (!(
    1.49
    (!(
    1.47
     constexpr
    1.37
    (
    1.32
    (`${
    1.29
    (((
    1.22
    Act Density 0.029%

    No Known Activations