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

    Neuronpedia

    INDEX
    Explanations

    overall goal and reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    일상
    0.48
    loading
    0.40
     beginner
    0.40
     непосред
    0.40
    きっかけ
    0.39
    region
    0.39
    account
    0.38
     உற்பத்தி
    0.38
     ईंधन
    0.38
    Carbon
    0.37
    POSITIVE LOGITS
     Nhiều
    0.57
    và
    0.52
     nhau
    0.51
     và
    0.49
     və
    0.48
     Và
    0.48
     mesmas
    0.48
     πολλ
    0.47
     και
    0.47
     Lobkovic
    0.47
    Act Density 0.001%

    No Known Activations