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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    textfield
    -0.08
    Judge
    -0.07
    .modify
    -0.07
    Reducer
    -0.07
    ۱۷
    -0.06
     Commissioner
    -0.06
     commissioner
    -0.06
    choice
    -0.06
     reserves
    -0.06
    .Priority
    -0.06
    POSITIVE LOGITS
    (){}↵↵
    0.07
    ???
    0.07
    );}↵
    0.06
     Ridley
    0.06
     hesab
    0.06
    icipant
    0.06
    囲
    0.06
     tuyệt
    0.06
    ++){
    0.06
    (qu
    0.06
    Act Density 0.005%

    No Known Activations