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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fa
    -0.08
     habitat
    -0.08
     forêt
    -0.07
     oeuvre
    -0.07
    left
    -0.07
     univers
    -0.07
    Vie
    -0.07
     laiss
    -0.07
    jón
    -0.07
     summar
    -0.07
    POSITIVE LOGITS
     ferramentas
    0.11
    工具
    0.11
     tools
    0.11
     herramientas
    0.11
     outils
    0.11
    -tools
    0.10
     Tools
    0.10
    .Tool
    0.10
     инструмент
    0.10
     инстру
    0.10
    Act Density 0.002%

    No Known Activations