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

    Neuronpedia

    INDEX
    Explanations

    nobody wants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нескольких
    0.46
     फंड
    0.46
    राहुल
    0.46
     राहुल
    0.46
     l
    0.45
    nPlease
    0.45
     شخصی
    0.45
     Ра
    0.45
     کچھ
    0.45
     ماہ
    0.45
    POSITIVE LOGITS
     unsteady
    0.45
     outcrops
    0.43
     outpost
    0.43
    远
    0.42
     antennas
    0.41
     unters
    0.40
    ⺈
    0.40
    ၊
    0.40
     uncontroll
    0.39
    白
    0.39
    Act Density 0.001%

    No Known Activations