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

    Neuronpedia

    INDEX
    Explanations

    Scientific/complex topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carry
    -0.07
     是
    -0.07
    	fp
    -0.06
    _log
    -0.06
    esehen
    -0.06
    是
    -0.06
     log
    -0.06
    Processed
    -0.06
     diplomat
    -0.06
    -0.06
    POSITIVE LOGITS
     Midlands
    0.06
    [prop
    0.06
    -contained
    0.06
     mã
    0.06
     травня
    0.06
    ifornia
    0.06
     Threads
    0.06
     vinyl
    0.06
     userModel
    0.06
    [sub
    0.06
    Act Density 0.129%

    No Known Activations