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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cash
    -0.06
     Kam
    -0.06
     sam
    -0.06
     Intel
    -0.06
     Tet
    -0.06
    ژ
    -0.06
     Insight
    -0.06
     disgrace
    -0.06
    ashion
    -0.06
    птом
    -0.06
    POSITIVE LOGITS
     spared
    0.07
     dreamed
    0.07
    。↵↵↵↵
    0.07
    842
    0.07
     MISSING
    0.06
    ordered
    0.06
    ी↵
    0.06
    puted
    0.06
     logger
    0.06
    /|
    0.06
    Act Density 0.016%

    No Known Activations