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

    Neuronpedia

    INDEX
    Explanations

    Accomplishments and discoveries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     echo
    -0.07
     ctypes
    -0.07
    ..........
    -0.07
     valign
    -0.07
    LineWidth
    -0.06
     Yeah
    -0.06
    /Delete
    -0.06
    ................................................................
    -0.06
    int
    -0.06
    ...
    -0.06
    POSITIVE LOGITS
    (fig
    0.06
    _CONSOLE
    0.06
    ALLY
    0.06
     은
    0.06
     BMW
    0.06
     tattoos
    0.06
     rtl
    0.06
     AMD
    0.06
     bathrooms
    0.06
     iris
    0.06
    Act Density 0.049%

    No Known Activations