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

    Neuronpedia

    INDEX
    Explanations

    technical and scientific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stands
    1.28
    𝗿
    1.24
    precise
    1.23
    att
    1.21
    inherited
    1.20
    ingen
    1.20
    un
    1.19
    en
    1.18
    i
    1.12
    km
    1.11
    POSITIVE LOGITS
     CarPlay
    1.32
     Ornament
    1.27
    于是
    1.27
     denn
    1.27
     оказался
    1.26
     Тео
    1.24
     KeyEvent
    1.23
     inscripción
    1.20
     sarebbe
    1.20
     って
    1.19
    Act Density 0.255%

    No Known Activations