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

    Neuronpedia

    INDEX
    Explanations

    fundamental mathematics concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    没
    0.43
    Regional
    0.43
    往
    0.43
    類
    0.42
    ኣ
    0.42
    B
    0.41
    target
    0.41
    們
    0.40
    regional
    0.40
     aun
    0.40
    POSITIVE LOGITS
    において
    0.78
    における
    0.76
     striving
    0.72
     essentials
    0.72
     strives
    0.72
     transcends
    0.69
     sehari
    0.68
     leveraging
    0.68
     grappling
    0.67
     emphasizing
    0.66
    Act Density 0.643%

    No Known Activations