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

    Neuronpedia

    INDEX
    Explanations

    list item formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    မ
    0.52
     rehearsals
    0.48
     Fellows
    0.48
    コレート
    0.48
     bookcases
    0.47
     showrooms
    0.46
    合わせ
    0.45
     dashboards
    0.45
     cottages
    0.44
     boosters
    0.44
    POSITIVE LOGITS
     ដោយ
    0.49
     жи
    0.48
    tempo
    0.48
     tulaj
    0.47
    ien
    0.46
    tro
    0.46
     मालिका
    0.46
     spol
    0.45
    ta
    0.45
     calific
    0.44
    Act Density 0.000%

    No Known Activations