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

    Neuronpedia

    INDEX
    Explanations

    poetic pronouncements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাবার
    0.49
     genauso
    0.48
     marrón
    0.48
     pretzels
    0.48
     cookware
    0.47
    を使って
    0.46
     gyerek
    0.46
    コラボ
    0.45
     verkauft
    0.45
    bikes
    0.45
    POSITIVE LOGITS
     grievous
    0.57
     weary
    0.53
     doubly
    0.50
     earnestly
    0.49
     thrice
    0.49
     thy
    0.47
     এইরূপ
    0.46
     behest
    0.45
     richly
    0.45
    æ
    0.44
    Act Density 0.127%

    No Known Activations