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

    Neuronpedia

    INDEX
    Explanations

    end of titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     okul
    0.29
    lingu
    0.27
     attribut
    0.26
     \&
    0.26
     ഏറ്റവും
    0.25
     le
    0.25
    kan
    0.25
    ꞎ
    0.25
     benutzer
    0.25
     Bezug
    0.24
    POSITIVE LOGITS
    ™,
    0.41
    ™.
    0.38
    ™
    0.37
    !”
    0.34
    !"
    0.31
    !:
    0.31
    ®,
    0.31
    !,
    0.30
    :
    0.30
    ®.
    0.30
    Act Density 0.370%

    No Known Activations