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

    Neuronpedia

    INDEX
    Explanations

    dates and soon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ată
    0.44
    Regarding
    0.44
    ל
    0.44
    plicht
    0.43
    ק
    0.41
    because
    0.41
    카
    0.41
    ס
    0.40
     permitting
    0.40
    ad
    0.40
    POSITIVE LOGITS
     nhiều
    0.50
     nhưng
    0.49
     pessoas
    0.46
     cherche
    0.44
     personnes
    0.43
     لكن
    0.40
     افراد
    0.40
     internally
    0.40
     setState
    0.39
     các
    0.39
    Act Density 0.009%

    No Known Activations