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

    Neuronpedia

    INDEX
    Explanations

    browser developer tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.28
     for
    1.24
    ない
    1.13
    ために
    1.12
    li
    0.97
    trav
    0.96
    트는
    0.94
    때
    0.94
    1
    0.94
    وم
    0.92
    POSITIVE LOGITS
    ك
    1.37
    $
    1.13
    in
    1.05
    ↵
    1.03
    رة
    1.00
    ,
    0.98
    ;
    0.96
    ה
    0.94
    h
    0.93
     في
    0.92
    Act Density 0.001%

    No Known Activations