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

    Neuronpedia

    INDEX
    Explanations

    geometry (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ிறோம்
    0.52
    dons
    0.52
     Negros
    0.51
     चौकी
    0.50
     reali
    0.49
    ataan
    0.48
    frozen
    0.48
    fection
    0.48
    フィック
    0.48
    ORMAL
    0.47
    POSITIVE LOGITS
     turbines
    0.52
    च
    0.49
     curvatures
    0.47
     bandages
    0.46
     ಸೇರಿದ
    0.45
    ต่ำ
    0.45
     cylinders
    0.44
     crowns
    0.44
     sympathies
    0.43
    かもしれませんが
    0.43
    Act Density 0.000%

    No Known Activations