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

    Neuronpedia

    INDEX
    Explanations

    cable management ties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agamanam
    0.70
     plano
    0.63
     coalitions
    0.62
    ీ
    0.62
     ၂
    0.61
     domine
    0.61
     )}$
    0.61
     democracies
    0.60
     calculi
    0.60
     browned
    0.59
    POSITIVE LOGITS
    :
    0.58
    [
    0.58
    ]
    0.54
    '
    0.53
    LC
    0.52
     hộ
    0.52
     vị
    0.52
     phạm
    0.52
    ಮ
    0.52
    ShowWindow
    0.51
    Act Density 0.001%

    No Known Activations