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

    Neuronpedia

    INDEX
    Explanations

    specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     połą
    0.43
     cięż
    0.40
     disque
    0.38
     stockage
    0.37
     matériau
    0.37
     이제
    0.36
    琛
    0.36
     어
    0.36
     umiejęt
    0.36
     avocat
    0.36
    POSITIVE LOGITS
     berkualitas
    0.57
    高品質
    0.52
     который
    0.48
     tertentu
    0.48
     अद्भुत
    0.47
     المختلفة
    0.47
     जिसकी
    0.45
     maupun
    0.44
    ที่มี
    0.44
    ដែលមាន
    0.44
    Act Density 0.039%

    No Known Activations