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

    Neuronpedia

    INDEX
    Explanations

    seeing to oneself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    embangkan
    0.83
     amélior
    0.77
    Improve
    0.76
     обеспечивает
    0.75
     improves
    0.75
     utilizes
    0.74
     compléter
    0.74
     sağlam
    0.74
     sağlar
    0.73
    حدد
    0.73
    POSITIVE LOGITS
     hearing
    1.99
     seeing
    1.96
     Seeing
    1.81
     witnessing
    1.73
     watching
    1.72
     Hearing
    1.72
    看到
    1.68
    Seeing
    1.65
    seeing
    1.64
     mendengar
    1.57
    Act Density 0.511%

    No Known Activations