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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eal
    0.54
    have
    0.53
    aginaw
    0.52
    iation
    0.51
    pygame
    0.50
    aros
    0.50
    araham
    0.49
    stir
    0.49
     aurora
    0.49
    ವನ್ನು
    0.48
    POSITIVE LOGITS
    OTE
    0.57
    逊
    0.53
    ,
    0.49
    _
    0.44
     J
    0.43
     mana
    0.43
     Y
    0.42
    ‌ها
    0.41
     preprint
    0.40
    NA
    0.40
    Act Density 0.000%

    No Known Activations