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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stay
    -0.07
    '↵↵↵↵
    -0.07
     Official
    -0.06
     symptoms
    -0.06
     output
    -0.06
    	el
    -0.06
    bastian
    -0.06
    átka
    -0.06
     �
    -0.06
     citrus
    -0.06
    POSITIVE LOGITS
    .Fatalf
    0.07
    폴
    0.07
     chaining
    0.07
    _EM
    0.07
     Islanders
    0.06
    _APB
    0.06
    uuid
    0.06
    FontSize
    0.06
     Pole
    0.06
     Biblical
    0.06
    Act Density 0.000%

    No Known Activations