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

    Neuronpedia

    INDEX
    Explanations

    approximate, attorney, council, post

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.98
    n
    1.94
    t
    1.77
    ला
    1.77
    R
    1.73
    oxymethyl
    1.65
     I
    1.62
    ，
    1.61
    at
    1.60
    y
    1.58
    POSITIVE LOGITS
    ﺎ
    1.89
    ции
    1.83
    ний
    1.82
     ткань
    1.65
    0
    1.65
    ist
    1.62
    5
    1.62
     Zusätzlich
    1.61
    Deux
    1.58
     Mesmo
    1.58
    Act Density 0.983%

    No Known Activations