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

    Neuronpedia

    INDEX
    Explanations

    access unauthorized data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ió
    0.54
     ie
    0.53
     واضح
    0.52
     female
    0.51
     tall
    0.51
     লম্বা
    0.50
    athin
    0.50
     ies
    0.49
     தன்னை
    0.49
     मोबाइल
    0.48
    POSITIVE LOGITS
    WindowTitle
    0.46
    SMTP
    0.46
    Vitamin
    0.45
     Wisdom
    0.45
     Epidemiology
    0.45
     Tac
    0.44
     View
    0.44
    AW
    0.44
     System
    0.43
    Method
    0.43
    Act Density 0.001%

    No Known Activations