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

    Neuronpedia

    INDEX
    Explanations

    tools used for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.78
    p
    0.73
    u
    0.71
    is
    0.70
    Penumpang
    0.65
    detail
    0.64
    team
    0.64
    world
    0.62
    i
    0.62
    IN
    0.61
    POSITIVE LOGITS
     tools
    1.23
     outils
    1.23
     herramientas
    1.16
    工具
    1.12
     Tools
    1.08
     narzęd
    1.08
     ferramentas
    1.05
     alat
    1.05
     herramienta
    1.05
     инструменты
    1.04
    Act Density 0.090%

    No Known Activations