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

    Neuronpedia

    INDEX
    Explanations

    adaptive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RAW
    -0.06
     año
    -0.06
    اب
    -0.06
     gắn
    -0.06
     atoi
    -0.06
     NSString
    -0.05
     nargin
    -0.05
     nors
    -0.05
     uğ
    -0.05
    isc
    -0.05
    POSITIVE LOGITS
     adaptive
    0.07
    یتی
    0.07
    ~-~-~-~-
    0.07
     indicated
    0.07
    但是
    0.06
     disposable
    0.06
     avoiding
    0.06
     ενώ
    0.06
     перед
    0.06
    ことで
    0.06
    Act Density 0.001%

    No Known Activations