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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contradict
    -0.08
    Auto
    -0.07
    Bruce
    -0.07
    (block
    -0.07
    Что
    -0.07
    Luke
    -0.07
    ("""↵
    -0.06
    double
    -0.06
    ché
    -0.06
    quote
    -0.06
    POSITIVE LOGITS
    in
    0.12
    IN
    0.12
     IN
    0.10
    -in
    0.09
     In
    0.08
    /in
    0.08
    .Win
    0.08
    In
    0.08
     in
    0.08
    ,in
    0.08
    Act Density 0.062%

    No Known Activations