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

    Neuronpedia

    INDEX
    Explanations

    checking or seeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     harus
    0.76
    正确的
    0.75
     correctly
    0.74
     phải
    0.74
     corretamente
    0.73
    正确
    0.73
    結局
    0.71
    igot
    0.69
     বৈঠকে
    0.68
     correto
    0.67
    POSITIVE LOGITS
     see
    2.93
     See
    2.58
    see
    2.53
    See
    2.47
     sees
    2.15
     SEE
    1.82
     voir
    1.76
     ببین
    1.72
    sees
    1.66
     Sees
    1.65
    Act Density 0.043%

    No Known Activations