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

    Neuronpedia

    INDEX
    Explanations

    swallowed whole by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ຫຼື
    0.47
    𝗵
    0.43
     cubrir
    0.42
     ወይም
    0.41
     talks
    0.41
    したり
    0.41
     charming
    0.40
    ཟ
    0.40
     고급
    0.40
     градусов
    0.40
    POSITIVE LOGITS
    ographe
    0.46
    setLayout
    0.45
     Compagnie
    0.43
    钦
    0.43
    Прави
    0.41
    راضي
    0.41
     العلمي
    0.40
     Univers
    0.40
    Scape
    0.40
    isière
    0.40
    Act Density 0.005%

    No Known Activations