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

    Neuronpedia

    INDEX
    Explanations

    parenthetical phrases and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Graphical
    0.41
    ්ර
    0.41
     graphical
    0.39
    0.38
    ほ
    0.37
     टूर्
    0.37
    〇
    0.37
     सुनहरा
    0.36
     moun
    0.36
     থাকিলে
    0.36
    POSITIVE LOGITS
     –
    0.81
     --
    0.76
     —
    0.71
     -
    0.68
    —
    0.64
     BUT
    0.61
    というか
    0.58
     (!)
    0.57
     ---
    0.56
    )—
    0.56
    Act Density 0.413%

    No Known Activations