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

    Neuronpedia

    INDEX
    Explanations

    function calls and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unterricht
    0.80
     alkaloids
    0.77
     lounging
    0.73
     tangy
    0.72
     adecuadas
    0.72
     Winnipeg
    0.71
     professores
    0.71
     distinguir
    0.71
     fortuit
    0.71
     Cómo
    0.71
    POSITIVE LOGITS
    (
    2.41
    ((
    1.79
    ([
    1.66
    （
    1.60
     (
    1.52
    ($
    1.51
    (\
    1.48
    ("
    1.45
    ('
    1.41
    ({
    1.41
    Act Density 0.152%

    No Known Activations