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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erosion
    -0.07
    -alt
    -0.07
     headings
    -0.07
    ogo
    -0.06
    ữa
    -0.06
    idian
    -0.06
    enden
    -0.06
     twitch
    -0.06
    rbrakk
    -0.06
    GV
    -0.06
    POSITIVE LOGITS
    ραση
    0.06
    }↵↵↵↵↵↵
    0.06
    �
    0.06
    числ
    0.06
    /add
    0.06
     Boot
    0.06
     Lt
    0.06
     Tul
    0.06
    	clear
    0.06
     �
    0.06
    Act Density 0.012%

    No Known Activations