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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     政
    -0.07
     Guards
    -0.07
     nutrit
    -0.07
    독
    -0.07
    -op
    -0.07
     shapes
    -0.07
     sử
    -0.06
    季
    -0.06
    urga
    -0.06
     있었
    -0.06
    POSITIVE LOGITS
    ICAST
    0.06
    /",↵
    0.06
    /images
    0.06
    /',↵
    0.06
    PRECATED
    0.06
     async
    0.06
    onitor
    0.06
    "';↵
    0.06
    ="@
    0.06
    usercontent
    0.06
    Act Density 0.051%

    No Known Activations