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

    Neuronpedia

    INDEX
    Explanations

    advice to yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     respectively
    0.86
    its
    0.83
    其
    0.78
     său
    0.78
     ஆகியவற்ற
    0.77
    விடும்
    0.76
     respectivamente
    0.76
     Its
    0.76
     આપે
    0.76
     its
    0.75
    POSITIVE LOGITS
     yourself
    1.41
    yourself
    1.24
     Yourself
    1.17
     نفسك
    1.16
    Your
    0.99
     jezelf
    0.98
     yourselves
    0.97
     your
    0.96
     thys
    0.88
     Your
    0.87
    Act Density 0.386%

    No Known Activations