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

    Neuronpedia

    INDEX
    Explanations

    Code and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuels
    -0.07
     giống
    -0.07
     lineman
    -0.07
     ';↵
    -0.06
    hotmail
    -0.06
    719
    -0.06
     phones
    -0.06
     Với
    -0.06
    	ti
    -0.06
            ↵    ↵
    -0.06
    POSITIVE LOGITS
    htub
    0.07
    θερ
    0.06
     postfix
    0.06
    Ö
    0.06
    う
    0.06
     ｀
    0.06
    ="/"
    0.06
    HttpContext
    0.06
     PCB
    0.06
    _Bool
    0.05
    Act Density 0.209%

    No Known Activations