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

    Neuronpedia

    INDEX
    Explanations

    list item 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ->
    0.83
    -
    0.78
     دیتی
    0.67
    repeated
    0.66
    r
    0.66
    t
    0.66
    _*
    0.65
    =
    0.65
    =>
    0.64
    ்
    0.64
    POSITIVE LOGITS
     Warhammer
    0.84
     USDC
    0.81
     broader
    0.78
     পিডিএফ
    0.76
     wider
    0.75
    琇
    0.75
    शेदपुर
    0.74
     altre
    0.73
     Pinnacle
    0.73
     Dominguez
    0.73
    Act Density 0.048%

    No Known Activations