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

    Neuronpedia

    INDEX
    Explanations

    advance directive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۸
    -0.06
     Enterprise
    -0.06
    slow
    -0.06
    .checkNotNull
    -0.06
    ,end
    -0.06
     speeds
    -0.06
     GEN
    -0.06
     usefulness
    -0.06
     entrega
    -0.06
    ativ
    -0.06
    POSITIVE LOGITS
     rozdíl
    0.08
            
↵        
↵
    0.07
    ↵    ↵    ↵
    0.06
     maxY
    0.06
    ",{
    0.06
    antiago
    0.06
    Unauthorized
    0.06
    '];
↵
    0.06
     )"
    0.06
     Dak
    0.06
    Act Density 0.004%

    No Known Activations