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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tries
    -0.07
     น
    -0.07
     lu
    -0.07
    可
    -0.07
    _hi
    -0.07
     Г
    -0.06
     («
    -0.06
    ailability
    -0.06
    _EMPTY
    -0.06
     faces
    -0.06
    POSITIVE LOGITS
     datasource
    0.06
    _View
    0.06
    REFERENCES
    0.06
     miscon
    0.06
    ERENCE
    0.06
    (Thread
    0.06
    機
    0.06
    Stamped
    0.06
    !!↵↵
    0.06
    (View
    0.05
    Act Density 0.019%

    No Known Activations