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

    Neuronpedia

    INDEX
    Explanations

    missing out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ук
    1.10
    тки
    1.05
    ിയ
    1.04
     Тру
    0.99
     Tay
    0.99
     rist
    0.94
     fijo
    0.93
     Kare
    0.93
    창
    0.90
    chodzi
    0.89
    POSITIVE LOGITS
    issauga
    1.28
    issippi
    1.20
     adhipp
    1.20
    ar
    1.19
    translational
    1.16
    फाइनल
    1.16
    ႉ
    1.13
    ا
    1.12
    serializing
    1.12
     inauguration
    1.09
    Act Density 0.026%

    No Known Activations