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

    Neuronpedia

    INDEX
    Explanations

    image descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simplification
    0.48
     grants
    0.47
     elementary
    0.46
     attainment
    0.45
     transmission
    0.43
     trasmissione
    0.43
     behov
    0.42
     reformulation
    0.42
     obtained
    0.42
    谱
    0.40
    POSITIVE LOGITS
    на
    0.51
     Up
    0.48
     পোকামাকড়
    0.47
    up
    0.45
    trashButton
    0.45
    大規模
    0.44
    Michael
    0.44
    ༻
    0.44
     〢
    0.44
     Monument
    0.44
    Act Density 0.019%

    No Known Activations