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

    Neuronpedia

    INDEX
    Explanations

    special markers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    holo
    0.61
    odium
    0.61
    汛
    0.60
    myItemType
    0.59
    oreet
    0.58
    ował
    0.58
    ovala
    0.57
     abundances
    0.57
     negat
    0.57
    odha
    0.57
    POSITIVE LOGITS
     ರೈ
    0.63
    タイヤ
    0.60
    机场
    0.58
    つ
    0.58
     सुनाई
    0.57
     কোথায়
    0.57
    telling
    0.56
     astronauts
    0.56
     eight
    0.56
     Missouri
    0.56
    Act Density 0.000%

    No Known Activations