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

    Neuronpedia

    INDEX
    Explanations

    exploitation and purchases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ম্ম
    0.48
     típica
    0.47
    тические
    0.46
     típico
    0.43
     benutzt
    0.43
    طات
    0.42
     ライン
    0.41
    铊
    0.41
    довле
    0.41
     типи
    0.41
    POSITIVE LOGITS
    re
    0.48
    kv
    0.46
    SubDirectoryPath
    0.46
    ponsorship
    0.45
    is
    0.45
    Tras
    0.45
    kt
    0.44
    agnar
    0.44
    st
    0.44
     νέ
    0.44
    Act Density 0.005%

    No Known Activations