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

    Neuronpedia

    INDEX
    Explanations

    technical and scientific research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    栤
    0.48
     делать
    0.46
    球队
    0.46
    делать
    0.46
     полити
    0.43
    麻烦
    0.42
    larından
    0.42
    收购
    0.42
    让人
    0.42
    很多
    0.42
    POSITIVE LOGITS
     mediated
    0.49
     during
    0.48
    mediated
    0.47
     w
    0.47
     dyads
    0.47
     despite
    0.46
     perturbed
    0.46
     under
    0.44
    における
    0.43
    cm
    0.42
    Act Density 0.041%

    No Known Activations