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

    Neuronpedia

    INDEX
    Explanations

    tools (various languages)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.79
    is
    0.75
    ри
    0.75
    team
    0.68
    ти
    0.66
    сия
    0.66
    detail
    0.65
    wireless
    0.65
    uose
    0.64
    Penumpang
    0.64
    POSITIVE LOGITS
     outils
    1.15
    工具
    1.13
     tools
    1.06
     herramientas
    1.06
     alat
    1.03
     herramienta
    1.01
     ferramentas
    0.98
     ferramenta
    0.98
     narzęd
    0.98
     Tools
    0.97
    Act Density 0.041%

    No Known Activations