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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     komen
    -0.06
    combination
    -0.06
     теч
    -0.06
    _part
    -0.06
     salaries
    -0.06
    (flag
    -0.06
    coach
    -0.06
    Ｃ
    -0.06
     suburb
    -0.06
     duplex
    -0.06
    POSITIVE LOGITS
    ()
↵
    0.06
                                                                    
    0.06
    #aa
    0.06
    ...)↵
    0.06
    paněl
    0.06
    =__
    0.06
     expansive
    0.06
     hern
    0.06
    TOP
    0.06
    _orders
    0.06
    Act Density 0.200%

    No Known Activations