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

    Neuronpedia

    INDEX
    Explanations

    error messages and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     แปร
    0.46
     encroachment
    0.46
    lavery
    0.45
    fromCharCode
    0.44
     stades
    0.44
     harboring
    0.43
    .)..
    0.41
    ঵
    0.41
    ディレクトリ
    0.41
     لفظ
    0.40
    POSITIVE LOGITS
    `:
    0.54
    ]:
    0.54
    ✨
    0.52
     LOOK
    0.51
     SEE
    0.50
     Xiaomi
    0.47
    :`
    0.46
     HID
    0.46
    ):
    0.45
     Barang
    0.45
    Act Density 0.000%

    No Known Activations