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

    Neuronpedia

    INDEX
    Explanations

    networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ков
    -0.07
     Bach
    -0.07
     brother
    -0.07
    ilent
    -0.07
    .setSize
    -0.06
     desktop
    -0.06
    matched
    -0.06
     rulers
    -0.06
     union
    -0.06
    aldo
    -0.06
    POSITIVE LOGITS
    Net
    0.08
     Network
    0.07
    lady
    0.07
    ){
↵
↵
    0.06
    orange
    0.06
    network
    0.06
    들
    0.06
    FLOW
    0.06
    .*;
↵
    0.06
     Pratt
    0.06
    Act Density 0.016%

    No Known Activations