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

    Neuronpedia

    INDEX
    Explanations

    start and manage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.47
    eu
    1.24
    o
    1.23
    eigen
    1.23
    🏻
    1.21
    delt
    1.19
    ∂
    1.18
     dotyczą
    1.17
    此
    1.15
    々の
    1.14
    POSITIVE LOGITS
     Luz
    1.28
    스
    1.27
    ן
    1.27
    benzoimidazole
    1.22
     cabe
    1.20
    이지
    1.20
     abelian
    1.20
    ности
    1.18
    胧
    1.18
     tenga
    1.16
    Act Density 0.000%

    No Known Activations