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

    Neuronpedia

    INDEX
    Explanations

    open curly brace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tal
    -0.08
    utton
    -0.08
     �
    -0.07
     resignation
    -0.07
    laring
    -0.07
     தேதி
    -0.07
     дату
    -0.07
     長
    -0.07
    оя
    -0.07
     ом
    -0.07
    POSITIVE LOGITS
    houses
    0.10
    Neighbors
    0.08
     home's
    0.08
     Representatives
    0.08
     Wholesale
    0.08
    တော့
    0.08
    Walls
    0.07
    Wholesale
    0.07
     marinade
    0.07
    Warp
    0.07
    Act Density 0.000%

    No Known Activations