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

    Neuronpedia

    INDEX
    Explanations

    Article snippet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Require
    -0.07
     Russ
    -0.07
    turtle
    -0.06
     contiguous
    -0.06
     entering
    -0.06
     boat
    -0.06
    ney
    -0.06
    инку
    -0.06
     Airways
    -0.06
     Rc
    -0.06
    POSITIVE LOGITS
    repr
    0.07
                    
↵
    0.06
    "{
    0.06
    ¨
    0.06
     crim
    0.06
    iane
    0.06
    �
    0.06
                   
↵
    0.06
     millions
    0.06
     непосред
    0.06
    Act Density 0.019%

    No Known Activations