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

    Neuronpedia

    INDEX
    Explanations

    providing notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     l
    0.71
    arın
    0.70
    erol
    0.68
    the
    0.62
    0.60
     fibrosis
    0.59
     VEGF
    0.59
     Initialization
    0.58
    0.57
    ↵↵
    0.57
    POSITIVE LOGITS
     as
    0.91
    К
    0.89
    notes
    0.83
    ية
    0.75
    يت
    0.75
    ב
    0.73
    B
    0.73
    可
    0.72
    好
    0.72
    ActionListener
    0.71
    Act Density 0.033%

    No Known Activations