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

    Neuronpedia

    INDEX
    Explanations

    Python libraries and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    忡
    0.78
    abor
    0.75
    issements
    0.73
     perfecting
    0.73
     perfected
    0.71
     कोस
    0.69
    isement
    0.68
    निवास
    0.68
     capacity
    0.67
    stones
    0.67
    POSITIVE LOGITS
     टि
    0.80
     সরকারি
    0.77
    เม
    0.77
    con
    0.77
    ロン
    0.76
    μα
    0.76
    ramid
    0.76
     আবারও
    0.75
     मुंबई
    0.75
    緣
    0.75
    Act Density 0.102%

    No Known Activations