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

    Neuronpedia

    INDEX
    Explanations

    installing specific software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    1.16
    liği
    1.09
    ২
    1.02
    ется
    1.02
    لی
    0.93
     što
    0.90
    ாலும்
    0.90
    ني
    0.89
    ObjectTemp
    0.88
    ية
    0.86
    POSITIVE LOGITS
    0
    1.60
    ل
    1.27
    l
    1.20
     for
    1.17
    ors
    1.16
    ल
    1.12
    ０
    1.09
     Installation
    1.05
     Install
    1.03
     Installing
    1.03
    Act Density 0.021%

    No Known Activations