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

    Neuronpedia

    INDEX
    Explanations

    GraphQL endpoint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이는
    0.78
     sogenannte
    0.77
     이유는
    0.77
     sogenannten
    0.76
    스는
    0.74
     Medicina
    0.73
     μιας
    0.73
    ďaka
    0.71
     ενός
    0.69
     Bride
    0.69
    POSITIVE LOGITS
    🚓
    0.86
     tersebut
    0.83
    🚤
    0.81
     했습니다
    0.80
    🚔
    0.79
     مذکور
    0.79
     failed
    0.78
     donation
    0.78
    🚙
    0.78
    ayscale
    0.78
    Act Density 0.486%

    No Known Activations