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

    Neuronpedia

    INDEX
    Explanations

    currency, status, and numeric values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ueness
    0.47
    inos
    0.46
    aren
    0.45
    ারি
    0.42
     SW
    0.42
    otides
    0.41
    ellige
    0.41
     جھنڈ
    0.41
     pinpoint
    0.40
    arları
    0.40
    POSITIVE LOGITS
    Asset
    0.47
    CP
    0.47
    Giá
    0.47
    Ñ
    0.44
    One
    0.44
    Object
    0.44
    Array
    0.43
    OpportunitiesBy
    0.43
    Danh
    0.43
     sécr
    0.42
    Act Density 0.000%

    No Known Activations