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

    Neuronpedia

    INDEX
    Explanations

    Foreign language technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    घर
    -0.08
    לק
    -0.08
    พ่
    -0.08
     명
    -0.08
    ახ
    -0.08
    981
    -0.07
     rêve
    -0.07
     droom
    -0.07
     第一
    -0.07
     Myst
    -0.07
    POSITIVE LOGITS
     approaches
    0.13
     approach
    0.12
     Vorge
    0.12
     Approach
    0.12
     abordagem
    0.12
     yaklaş
    0.12
    Appro
    0.11
     approche
    0.10
     APPRO
    0.10
     подход
    0.10
    Act Density 0.006%

    No Known Activations