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

    Neuronpedia

    INDEX
    Explanations

    references and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (filters
    -0.08
    幸
    -0.07
     싶
    -0.07
    Piece
    -0.06
     біл
    -0.06
    soc
    -0.06
    rob
    -0.06
    онт
    -0.06
     wget
    -0.06
     Download
    -0.06
    POSITIVE LOGITS
     Sandra
    0.07
     للم
    0.07
    IRM
    0.07
     Alexandra
    0.07
    给
    0.07
     received
    0.06
     Illinois
    0.06
     جر
    0.06
     supern
    0.06
     bios
    0.06
    Act Density 0.020%

    No Known Activations