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

    Neuronpedia

    INDEX
    Explanations

    parentheses and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    approval
    -0.06
    .Exception
    -0.06
     Willis
    -0.06
    瑟
    -0.06
     boosts
    -0.06
    STALL
    -0.06
    (order
    -0.06
    numbers
    -0.06
    autoreleasepool
    -0.06
    awei
    -0.06
    POSITIVE LOGITS
    rif
    0.07
    .callbacks
    0.06
    ประมาณ
    0.06
     karşılaş
    0.06
    куля
    0.06
     econom
    0.06
    ायल
    0.06
    .btnDelete
    0.06
     Inventory
    0.06
    .""
    0.06
    Act Density 0.126%

    No Known Activations