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

    Neuronpedia

    INDEX
    Explanations

    place in my life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ira
    0.63
    يا
    0.63
    ün
    0.61
     يمكن
    0.57
    ach
    0.54
    un
    0.53
     absence
    0.53
     eine
    0.53
    ight
    0.52
    वा
    0.52
    POSITIVE LOGITS
    ถี่
    0.53
     Citizenship
    0.52
    🗞
    0.50
    transfer
    0.49
    programme
    0.48
     Entscheid
    0.48
     Chakraborty
    0.47
    esquerdo
    0.46
     Великобрита
    0.46
     Deer
    0.45
    Act Density 0.000%

    No Known Activations