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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     umož
    -0.07
     عدم
    -0.07
     licking
    -0.06
    avg
    -0.06
     LT
    -0.06
    Không
    -0.06
     Wiki
    -0.06
     těchto
    -0.06
     nurt
    -0.06
    ược
    -0.06
    POSITIVE LOGITS
    _finder
    0.07
     accountability
    0.06
     alright
    0.06
    _ax
    0.06
     kingdoms
    0.06
    711
    0.06
     Ã
    0.06
    emploi
    0.06
     gonna
    0.06
    ś
    0.06
    Act Density 0.056%

    No Known Activations