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

    Neuronpedia

    INDEX
    Explanations

    reception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (draw
    -0.07
    Modification
    -0.06
    axed
    -0.06
     життя
    -0.06
     BLUE
    -0.06
     даних
    -0.06
     thwart
    -0.06
     fantasies
    -0.06
    -chief
    -0.06
    ARIANT
    -0.06
    POSITIVE LOGITS
    těl
    0.07
    opcion
    0.07
     farmhouse
    0.06
    %%↵
    0.06
     Buccaneers
    0.06
     signaling
    0.06
    .urlencoded
    0.06
     quarterback
    0.06
    .drawImage
    0.06
     imageURL
    0.06
    Act Density 0.002%

    No Known Activations