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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	NSString
    -0.07
    ﮏ
    -0.07
    ossible
    -0.07
    .ContextCompat
    -0.07
    캑
    -0.07
    코
    -0.07
     strncpy
    -0.07
    醑
    -0.07
     nackte
    -0.06
    ᄀ
    -0.06
    POSITIVE LOGITS
     elephant
    0.08
     Strauss
    0.07
     syst
    0.07
    socket
    0.07
     QUESTION
    0.07
    _EXTENSIONS
    0.07
     situations
    0.07
    _RESET
    0.07
    流浪
    0.07
    roles
    0.07
    Act Density 0.001%

    No Known Activations