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

    Neuronpedia

    INDEX
    Explanations

    why and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    equity
    0.50
    in
    0.49
    a
    0.48
    is
    0.45
     jurisdiction
    0.44
    suppliers
    0.43
    e
    0.43
    %
    0.43
    opportunity
    0.41
     base
    0.41
    POSITIVE LOGITS
     Wochen
    0.53
     settimana
    0.47
     እነዚህ
    0.47
     മണിക്ക
    0.47
     Stunden
    0.46
     tygod
    0.46
     nonché
    0.46
    或许
    0.44
     หรือ
    0.44
     Rocks
    0.44
    Act Density 0.001%

    No Known Activations