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

    Neuronpedia

    INDEX
    Explanations

    associated with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.43
     acup
    0.43
     OTHER
    0.40
     symbolized
    0.39
     financed
    0.38
     વિવિધ
    0.38
    from
    0.38
    中の
    0.38
    onc
    0.38
    ursa
    0.37
    POSITIVE LOGITS
    عب
    0.45
    यश
    0.41
     Verfü
    0.39
    Sie
    0.39
    inertia
    0.38
     Popov
    0.37
     opis
    0.37
     Verma
    0.37
     Sie
    0.37
     permas
    0.37
    Act Density 0.001%

    No Known Activations