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

    Neuronpedia

    INDEX
    Explanations

    mostly cloudy with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redirects
    1.03
    కుంట
    1.02
     dup
    1.02
    ように
    0.99
    ཟ
    0.99
     vendor
    0.99
     cling
    0.98
     মঙ্গল
    0.97
     e
    0.97
    不良
    0.96
    POSITIVE LOGITS
    ctuation
    1.21
    ções
    1.19
     चाहिये
    1.10
    ството
    1.10
    nent
    1.04
    ൮
    1.03
    സര്‍
    1.02
    ੀ
    1.01
    ர்
    1.00
    enciado
    1.00
    Act Density 0.001%

    No Known Activations