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

    Neuronpedia

    INDEX
    Explanations

    technical definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hozzá
    0.38
    ュー
    0.38
     स्कैनर
    0.37
     appren
    0.37
     istem
    0.37
     giz
    0.37
    𝗬
    0.36
     tapp
    0.35
    ڈ
    0.35
     lice
    0.35
    POSITIVE LOGITS
    \(
    0.40
    erequisites
    0.38
    two
    0.38
    five
    0.37
    等地
    0.36
     написа
    0.35
    emonic
    0.35
     написано
    0.35
    locations
    0.35
    वाली
    0.34
    Act Density 0.059%

    No Known Activations