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

    Neuronpedia

    INDEX
    Explanations

    business, plans, and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .#
    0.52
     chante
    0.50
     nrows
    0.47
     repaint
    0.45
     modality
    0.45
    民众
    0.45
    王的
    0.43
     রঙের
    0.42
    倰
    0.42
     redo
    0.42
    POSITIVE LOGITS
    A
    0.56
    L
    0.55
    as
    0.54
    am
    0.54
    B
    0.50
    та
    0.50
    aca
    0.48
    and
    0.48
    business
    0.48
     chương
    0.47
    Act Density 0.000%

    No Known Activations